© 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. 5535
    Prev
    Next
    INDEX
    Explanations

    programming syntax and data structure terminology

    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
    27
    +0.11
    0.5%
    289
    +0.11
    0.5%
    273
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.11
    0.08
    107
    +0.11
    0.06
    314
    +0.10
    0.00
    Negative Logits
     conclud
    -0.81
     vide
    -0.67
     empowering
    -0.64
     liberated
    -0.63
     unstable
    -0.62
     interven
    -0.62
    emort
    -0.62
     turmoil
    -0.61
     somehow
    -0.60
     Directors
    -0.60
    POSITIVE LOGITS
    hound
    1.12
    leaf
    1.11
    bones
    1.08
    weed
    1.07
    words
    1.07
    cone
    1.06
    lighting
    1.05
    spr
    1.05
    bane
    1.05
    light
    1.05
    Activations Density 0.395%

    No Known Activations