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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 45404
    Prev
    Next
    INDEX
    Explanations

    phrases related to political activism and fundraising

    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
    97
    +0.02
    0.5%
    127
    +0.02
    0.5%
    670
    +0.02
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.02
    0.24
    64
    +0.02
    -0.13
    107
    +0.02
    0.08
    Negative Logits
    meal
    -0.12
     Mandarin
    -0.12
    nery
    -0.11
    raw
    -0.11
    lists
    -0.11
     bis
    -0.11
     snipp
    -0.11
    cue
    -0.11
    rip
    -0.11
    ifi
    -0.11
    POSITIVE LOGITS
    imar
    0.13
    ulic
    0.13
    erest
    0.13
     Lights
    0.13
    Stud
    0.13
    est
    0.13
    KEN
    0.12
    xon
    0.12
    anish
    0.12
    Shock
    0.12
    Activations Density 3.961%

    No Known Activations