© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4541
    Prev
    Next
    INDEX
    Explanations

    the names of specific individuals, particularly those associated with achievements or roles

    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
    251
    +0.11
    0.5%
    205
    +0.10
    0.5%
    649
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.02
    659
    +0.10
    0.02
    538
    +0.10
    0.01
    Negative Logits
     inhibitors
    -0.81
     bund
    -0.73
    andum
    -0.67
     Shooter
    -0.67
    qus
    -0.62
     palms
    -0.61
     inhibitor
    -0.61
     cannabin
    -0.61
     bait
    -0.58
     unemploy
    -0.58
    POSITIVE LOGITS
    een
    0.99
    isf
    0.97
    sburgh
    0.95
    say
    0.92
    enberg
    0.92
    sburg
    0.87
    erella
    0.85
    eah
    0.85
    rift
    0.83
    zman
    0.83
    Activations Density 0.049%

    No Known Activations