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. 4398
    Prev
    Next
    INDEX
    Explanations

    Turkish words or phrases

    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
    +0.14
    1.0%
    314
    +0.08
    0.6%
    126
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.14
    0.47
    160
    +0.08
    0.29
    64
    +0.08
    -0.24
    Negative Logits
    hement
    -0.45
     midway
    -0.41
     sophomore
    -0.40
     Leah
    -0.38
     Devin
    -0.38
     Shaun
    -0.38
    opoulos
    -0.37
     Hogan
    -0.37
     Donna
    -0.37
     trek
    -0.37
    POSITIVE LOGITS
    Below
    0.56
    pmwiki
    0.52
    ocations
    0.51
    tymology
    0.50
    ":[{"
    0.48
    ":["
    0.47
    hemat
    0.46
    versions
    0.46
    English
    0.46
    ccording
    0.45
    Activations Density 12.240%

    No Known Activations