© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 7415
    Prev
    Next
    INDEX
    Explanations

    references to organizations and institutions

    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
    320
    +0.11
    0.5%
    123
    +0.09
    0.4%
    55
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.11
    -0.03
    224
    +0.09
    0.10
    288
    +0.09
    0.13
    Negative Logits
     LV
    -0.72
    ãĥĢ
    -0.71
    ãĥĨ
    -0.68
    Bul
    -0.67
    ãĥł
    -0.67
    Lear
    -0.66
    Õ
    -0.65
    izoph
    -0.65
    âϦ
    -0.64
     LW
    -0.64
    POSITIVE LOGITS
     applauded
    1.00
     congratulated
    0.99
     agrees
    0.97
     reacted
    0.96
     testified
    0.90
     urged
    0.90
     joked
    0.89
     denounced
    0.88
     told
    0.88
     said
    0.87
    Activations Density 1.647%

    No Known Activations