Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45574
    Prev
    Next
    INDEX
    Explanations

    adjectives related to physical attributes or abilities, especially being right-handed

    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
    +0.05
    0.4%
    568
    +0.05
    0.4%
    371
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.05
    0.07
    713
    +0.05
    0.04
    435
    +0.05
    0.03
    Negative Logits
    anamo
    -0.44
    adium
    -0.40
    idian
    -0.39
    liam
    -0.38
    ablish
    -0.37
    CHAT
    -0.36
    burgh
    -0.36
    ublic
    -0.36
    yll
    -0.36
    aroo
    -0.36
    POSITIVE LOGITS
     nodd
    0.47
    ness
    0.47
    handed
    0.45
     luggage
    0.40
     clutch
    0.39
     stroke
    0.38
     crane
    0.38
     thumb
    0.37
     needle
    0.36
    erers
    0.35
    Activations Density 13.461%

    No Known Activations