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. 40193
    Prev
    Next
    INDEX
    Explanations

    specific mentions of "Chamber" in a governmental or legislative context

    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
    +0.18
    0.9%
    447
    +0.16
    0.8%
    35
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.21
    575
    +0.16
    0.14
    216
    +0.12
    0.08
    Negative Logits
     Wass
    -0.64
    ces
    -0.60
    ynasty
    -0.56
     curfew
    -0.56
    DER
    -0.55
    hig
    -0.54
     sporadic
    -0.53
     cheapest
    -0.53
     Kindle
    -0.52
    uras
    -0.52
    POSITIVE LOGITS
    lain
    1.55
    maid
    1.01
    house
    0.90
     chambers
    0.87
     chamber
    0.87
    ambers
    0.80
     Chamber
    0.77
    door
    0.76
    ophon
    0.73
     Chambers
    0.73
    Activations Density 7.824%

    No Known Activations