© 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. 4459
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly parameters related to dimensions and characteristics

    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
    +0.18
    0.8%
    312
    +0.11
    0.5%
    198
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.18
    0.02
    326
    +0.11
    0.04
    488
    +0.10
    0.04
    Negative Logits
     Newsletter
    -0.81
    £ı
    -0.75
    allo
    -0.73
    OUP
    -0.70
    ividual
    -0.70
    gio
    -0.66
    atech
    -0.66
     Progressive
    -0.66
    ythm
    -0.66
    andum
    -0.65
    POSITIVE LOGITS
     latitude
    0.83
    76561
    0.80
     inhabited
    0.78
    width
    0.76
    height
    0.74
     magnification
    0.73
    north
    0.72
    MpServer
    0.72
    Height
    0.71
     occupied
    0.70
    Activations Density 0.195%

    No Known Activations