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. 40122
    Prev
    Next
    INDEX
    Explanations

    word stems related to technology and information security

    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
    385
    +0.10
    0.6%
    276
    +0.10
    0.6%
    554
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.24
    288
    +0.10
    0.24
    709
    +0.09
    0.14
    Negative Logits
    EStream
    -0.66
    ģ«
    -0.66
    rator
    -0.65
    rators
    -0.63
    anooga
    -0.62
     srf
    -0.60
    urities
    -0.58
    maxwell
    -0.58
    Ͻ
    -0.58
    anova
    -0.56
    POSITIVE LOGITS
    phrine
    0.76
    toe
    0.69
     tro
    0.66
    tsky
    0.63
    lli
    0.53
    tted
    0.52
    tl
    0.52
     coli
    0.50
     stride
    0.50
    oidal
    0.50
    Activations Density 8.185%

    No Known Activations