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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 6-RES_POST_32K-OAI
    6. 4254
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to software package management and installation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_6.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.18
    0.8%
    165
    +0.10
    0.5%
    106
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.18
    0.09
    160
    +0.10
    0.06
    314
    +0.09
    0.02
    Negative Logits
     Spiel
    -0.77
     magnets
    -0.72
     enthus
    -0.68
     Vanderbilt
    -0.64
     passionate
    -0.64
     Carlton
    -0.62
     outwe
    -0.61
     arson
    -0.60
     exhib
    -0.60
     abound
    -0.60
    POSITIVE LOGITS
    undo
    0.84
    elvet
    0.78
    irlf
    0.77
    iban
    0.75
     Alternatively
    0.75
    renheit
    0.75
    igr
    0.75
    Alternatively
    0.74
    osterone
    0.74
    orage
    0.74
    Activations Density 0.323%

    No Known Activations