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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 13554
    Prev
    Next
    INDEX
    Explanations

    German words and phrases amidst English 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
    39
    +0.05
    0.5%
    754
    +0.05
    0.5%
    294
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.05
    0.23
    326
    +0.05
    0.20
    575
    +0.05
    0.13
    Negative Logits
    SHIP
    -0.44
    MET
    -0.41
    CHR
    -0.41
    SC
    -0.36
     ministry
    -0.35
    MIT
    -0.34
    д
    -0.34
    SL
    -0.34
    DF
    -0.33
    strings
    -0.33
    POSITIVE LOGITS
    ained
    0.52
    asing
    0.52
    urch
    0.51
    andise
    0.51
    arted
    0.50
    arak
    0.47
    okemon
    0.47
    atche
    0.46
    eneg
    0.46
    aining
    0.46
    Activations Density 6.536%

    No Known Activations