© 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. 4845
    Prev
    Next
    INDEX
    Explanations

    elements related to specific identifiers or classification codes

    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
    440
    +0.10
    0.5%
    348
    +0.10
    0.5%
    68
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.03
    326
    +0.10
    0.03
    220
    +0.10
    0.02
    Negative Logits
    etsk
    -0.78
    forth
    -0.78
    bara
    -0.76
    ctors
    -0.73
    urat
    -0.71
    cific
    -0.69
    ctor
    -0.68
    earch
    -0.68
    illard
    -0.67
    istically
    -0.65
    POSITIVE LOGITS
    Textures
    0.70
    é¾įåĸļ士
    0.67
     Telescope
    0.66
    ãĥķãĤ©
    0.66
     gamers
    0.63
    çķ
    0.62
    ãĥİ
    0.61
    ãĥ´
    0.61
    é¾įå
    0.61
     Holo
    0.61
    Activations Density 0.132%

    No Known Activations