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

    Neuronpedia

    Jacobian LensNEW
    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. 5055
    Prev
    Next
    INDEX
    Explanations

    numerical references that relate to technical specifications or measurements

    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
    373
    +0.21
    1.0%
    261
    +0.10
    0.4%
    594
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.21
    0.03
    488
    +0.10
    0.04
    594
    +0.10
    0.03
    Negative Logits
    thood
    -0.74
    chwitz
    -0.70
    emen
    -0.66
    osate
    -0.66
    itism
    -0.65
    usterity
    -0.64
    bish
    -0.63
    Orig
    -0.62
     Ethiopian
    -0.62
     Moroccan
    -0.62
    POSITIVE LOGITS
    â̲
    0.74
     preferably
    0.73
     disposed
    0.72
    (\
    0.69
     circuitry
    0.68
     bounded
    0.68
     positioned
    0.68
     detects
    0.67
     FIG
    0.66
     intersect
    0.66
    Activations Density 0.166%

    No Known Activations