© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40071
    Prev
    Next
    INDEX
    Explanations

    words related to advertisements or promotions

    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
    +0.18
    1.0%
    195
    +0.12
    0.6%
    274
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.18
    0.10
    481
    +0.12
    0.28
    288
    +0.09
    0.27
    Negative Logits
    ARD
    -0.64
    falls
    -0.59
    bred
    -0.57
    MENTS
    -0.54
    cies
    -0.54
    tto
    -0.53
    jiang
    -0.52
    dogs
    -0.52
    ardy
    -0.52
     Kardashian
    -0.51
    POSITIVE LOGITS
    ync
    0.80
    omnia
    0.77
    izoph
    0.73
    ixel
    0.71
    idia
    0.69
    hid
    0.69
    Gam
    0.67
    MpServer
    0.64
    idy
    0.63
    igmatic
    0.63
    Activations Density 17.022%

    No Known Activations