© 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. 5499
    Prev
    Next
    INDEX
    Explanations

    references to academic and athletic grade levels

    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
    575
    +0.12
    0.5%
    356
    +0.11
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.12
    0.02
    372
    +0.11
    0.02
    711
    +0.11
    0.02
    Negative Logits
    pots
    -0.84
    ioned
    -0.84
    ichick
    -0.83
    rosis
    -0.81
    atari
    -0.71
    pel
    -0.70
    tering
    -0.70
    zsche
    -0.69
    rosc
    -0.68
    abled
    -0.68
    POSITIVE LOGITS
     slump
    0.86
     year
    0.81
     college
    0.74
     dorm
    0.73
    omore
    0.70
     senate
    0.69
     senator
    0.68
     hur
    0.67
    olesc
    0.66
     batch
    0.64
    Activations Density 0.138%

    No Known Activations