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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8725
    Prev
    Next
    INDEX
    Explanations

    words related to discovery and recognition of new or previously overlooked content

    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
    680
    +0.10
    0.5%
    221
    +0.09
    0.4%
    91
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.10
    0.07
    362
    +0.09
    0.06
    91
    +0.09
    0.05
    Negative Logits
    alos
    -0.86
     teasp
    -0.86
    ãĥ¼ãĥ«
    -0.79
    athy
    -0.77
    ©¶æ
    -0.76
    esson
    -0.74
    omever
    -0.74
    orously
    -0.72
    vertisement
    -0.72
    claimer
    -0.71
    POSITIVE LOGITS
     superpower
    0.64
     secrets
    0.64
     notions
    0.64
     attractions
    0.63
     demographic
    0.63
     geopolitical
    0.61
     international
    0.61
     auxiliary
    0.60
     secret
    0.59
     joint
    0.59
    Activations Density 0.438%

    No Known Activations