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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 33240
    Prev
    Next
    INDEX
    Explanations

    content related to subscription, pricing, and promotional offers in texts related to journalism and news

    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
    640
    +0.15
    1.1%
    447
    +0.07
    0.5%
    20
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.55
    64
    +0.07
    -0.26
    6
    +0.07
    0.28
    Negative Logits
    anke
    -0.52
    icter
    -0.52
    amera
    -0.50
    ythm
    -0.45
     mosqu
    -0.43
    velt
    -0.42
    uph
    -0.41
     Princ
    -0.41
     Azerb
    -0.40
    leck
    -0.40
    POSITIVE LOGITS
    WASHINGTON
    0.60
    TON
    0.59
    Loading
    0.56
    PROV
    0.53
    Page
    0.53
    CLE
    0.53
    Copyright
    0.51
    ³³
    0.51
    PLIC
    0.51
    Article
    0.51
    Activations Density 15.096%

    No Known Activations