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. 45432
    Prev
    Next
    INDEX
    Explanations

    words related to password security and encryption techniques

    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
    174
    +0.10
    0.6%
    447
    +0.09
    0.6%
    444
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.10
    0.09
    57
    +0.09
    0.06
    326
    +0.09
    0.19
    Negative Logits
    lessly
    -0.66
    cam
    -0.61
    lund
    -0.54
    hips
    -0.53
    lighting
    -0.52
    ships
    -0.52
    say
    -0.52
    dq
    -0.51
    RAY
    -0.51
     glim
    -0.50
    POSITIVE LOGITS
    plain
    0.75
    ption
    0.67
    plin
    0.67
    illes
    0.65
    ffiti
    0.65
    ppa
    0.64
    quer
    0.63
    plan
    0.62
    ften
    0.61
    ivari
    0.60
    Activations Density 6.820%

    No Known Activations