© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 40617
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the phrase "know it", as well as references to the concept of having an additional opportunity or chance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.13
    0.5%
    393
    +0.12
    0.5%
    431
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.13
    0.28
    640
    +0.12
    0.24
    160
    +0.09
    0.19
    Negative Logits
    hement
    -0.81
     sidx
    -0.81
    erate
    -0.79
    etheus
    -0.79
    utterstock
    -0.75
    rative
    -0.75
    vertisement
    -0.74
    edia
    -0.74
    uably
    -0.74
    rary
    -0.73
    POSITIVE LOGITS
     firsthand
    0.85
     beforehand
    0.75
     intimately
    0.73
     instinctively
    0.73
     whereabouts
    0.69
    CHAT
    0.69
     secret
    0.68
    nothing
    0.68
    ledged
    0.67
     existence
    0.65
    Activations Density 14.234%

    No Known Activations