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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5518
    Prev
    Next
    INDEX
    Explanations

    instances of the word "form" and its variations, indicating discussions around structure or organization

    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
    208
    +0.14
    0.6%
    36
    +0.09
    0.4%
    70
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.03
    588
    +0.09
    0.02
    208
    +0.09
    0.02
    Negative Logits
    mine
    -0.67
     Bees
    -0.63
    EStream
    -0.61
    nea
    -0.61
    minent
    -0.60
    mins
    -0.60
    lua
    -0.59
    chy
    -0.59
     Dodgers
    -0.58
     provocation
    -0.58
    POSITIVE LOGITS
    ational
    1.24
    idable
    1.16
    atted
    1.11
    aldehyde
    1.07
    ula
    1.01
    ulations
    1.00
    ities
    0.97
    ative
    0.96
    ulate
    0.94
    ulation
    0.90
    Activations Density 0.126%

    No Known Activations