© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4677
    Prev
    Next
    INDEX
    Explanations

    references to intravenous therapy and related medical terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    328
    +0.13
    0.6%
    231
    +0.12
    0.5%
    83
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.13
    0.01
    404
    +0.12
    0.01
    530
    +0.10
    0.01
    Negative Logits
    geist
    -0.75
    Else
    -0.68
    dylib
    -0.66
    alty
    -0.66
    ppings
    -0.64
    naire
    -0.64
    vironment
    -0.64
    pherd
    -0.63
    âĸ¬
    -0.62
    expr
    -0.62
    POSITIVE LOGITS
    ISION
    0.95
    ORY
    0.90
    itals
    0.85
    ayne
    0.83
    inal
    0.73
    ricular
    0.73
    ENTS
    0.72
    ITAL
    0.72
    ested
    0.71
    ility
    0.71
    Activations Density 0.030%

    No Known Activations