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

    Neuronpedia

    Jacobian LensNEW
    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. 33512
    Prev
    Next
    INDEX
    Explanations

    words related to "lots" or "lots of" in various contexts

    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
    +0.19
    0.8%
    7
    +0.11
    0.5%
    19
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    590
    +0.19
    0.07
    288
    +0.11
    0.17
    442
    +0.11
    0.06
    Negative Logits
    perty
    -0.74
     whistlebl
    -0.69
     testim
    -0.69
    igent
    -0.68
    ando
    -0.67
    Adv
    -0.67
     distingu
    -0.67
    ctl
    -0.66
    arthed
    -0.63
     streng
    -0.62
    POSITIVE LOGITS
    tery
    1.36
    ter
    0.95
    stones
    0.89
    lights
    0.81
    loads
    0.81
    uses
    0.81
    oys
    0.79
    creen
    0.78
    Lot
    0.78
    blocks
    0.75
    Activations Density 6.900%

    No Known Activations