© 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. 5496
    Prev
    Next
    INDEX
    Explanations

    timestamps and references to time in text

    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
    +0.23
    1.1%
    300
    +0.09
    0.4%
    762
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.04
    6
    +0.09
    0.03
    160
    +0.09
    0.03
    Negative Logits
     Marathon
    -0.65
    Rated
    -0.63
     bios
    -0.63
     Cosmos
    -0.61
    onite
    -0.60
    iris
    -0.60
    olor
    -0.60
     diffusion
    -0.59
     biod
    -0.58
     Quart
    -0.57
    POSITIVE LOGITS
    HAHA
    0.89
    hm
    0.82
    nah
    0.79
    HAHAHAHA
    0.79
    Fuck
    0.77
    Eh
    0.70
    女
    0.69
     WHY
    0.68
     Shit
    0.68
    ¬¼
    0.66
    Activations Density 0.097%

    No Known Activations