© 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. 4959
    Prev
    Next
    INDEX
    Explanations

    phrases related to absence or disappearance

    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
    108
    +0.09
    0.4%
    534
    +0.09
    0.4%
    306
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.09
    0.04
    762
    +0.09
    0.05
    351
    +0.09
    0.03
    Negative Logits
     antioxid
    -0.83
     portfolios
    -0.65
    æ©Ł
    -0.61
     PsyNet
    -0.59
    Ess
    -0.58
     today
    -0.58
    Leaks
    -0.57
    BP
    -0.57
     Essential
    -0.57
    Thom
    -0.55
    POSITIVE LOGITS
    theless
    1.05
    rences
    0.88
    thood
    0.82
    mind
    0.73
     dreamed
    0.73
    before
    0.72
    onies
    0.70
    cation
    0.69
    ratch
    0.68
    erer
    0.68
    Activations Density 0.350%

    No Known Activations