© 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. 3807
    Prev
    Next
    INDEX
    Explanations

    words related to hoods or areas related to local communities

    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
    288
    +0.12
    0.6%
    447
    +0.12
    0.6%
    365
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.12
    0.08
    558
    +0.12
    0.06
    11
    +0.11
    0.04
    Negative Logits
    lihood
    -0.78
    ngth
    -0.76
    ãĤ´ãĥ³
    -0.74
    andum
    -0.70
    tery
    -0.65
    ×ķ
    -0.62
    FORM
    -0.61
    vasive
    -0.61
    ASED
    -0.61
    MENT
    -0.60
    POSITIVE LOGITS
    oos
    0.93
    skin
    0.88
    ed
    0.87
     hood
    0.87
    ie
    0.86
     ornament
    0.85
    sie
    0.84
    tip
    0.83
    ook
    0.78
    ies
    0.76
    Activations Density 6.608%

    No Known Activations