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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 34290
    Prev
    Next
    INDEX
    Explanations

    statistics and figures related to sports

    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
    27
    +0.06
    0.5%
    463
    +0.06
    0.5%
    441
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.06
    0.17
    107
    +0.06
    0.06
    373
    +0.06
    -0.14
    Negative Logits
     sett
    -0.37
     radi
    -0.35
     crest
    -0.34
     mature
    -0.33
     resize
    -0.33
     transport
    -0.32
     Transport
    -0.32
     comm
    -0.32
     paed
    -0.32
     peer
    -0.32
    POSITIVE LOGITS
    Buff
    0.41
    ãĤ¸
    0.41
    PsyNetMessage
    0.41
    Ont
    0.39
    OUR
    0.38
    Ĥİ
    0.38
    é¾įå
    0.36
    --+
    0.36
    TING
    0.36
    Beck
    0.36
    Activations Density 5.352%

    No Known Activations