© 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. 32853
    Prev
    Next
    INDEX
    Explanations

    information or situations coming to light, often related to controversies or investigations

    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
    459
    +0.14
    0.7%
    447
    +0.10
    0.5%
    642
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.14
    0.21
    563
    +0.10
    0.10
    442
    +0.09
    0.07
    Negative Logits
    regor
    -0.69
    okia
    -0.69
    apons
    -0.67
    ettings
    -0.64
    halla
    -0.63
     apologize
    -0.62
    apter
    -0.61
    irlf
    -0.61
     Rampage
    -0.59
    uador
    -0.59
    POSITIVE LOGITS
    enment
    0.95
    weights
    0.93
    lights
    0.93
     bulb
    0.84
    hearted
    0.81
    ening
    0.80
    ener
    0.78
    bul
    0.77
     shone
    0.76
    eners
    0.76
    Activations Density 7.057%

    No Known Activations