© 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. 5160
    Prev
    Next
    INDEX
    Explanations

    numerical data or time codes

    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
    207
    +0.15
    0.7%
    12
    +0.13
    0.6%
    532
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.15
    0.03
    166
    +0.13
    0.03
    93
    +0.12
    0.04
    Negative Logits
    Mus
    -0.81
     Kats
    -0.79
     Kun
    -0.78
     Beaut
    -0.77
    Wil
    -0.76
    KB
    -0.75
     Pupp
    -0.75
     Mercenary
    -0.75
    mus
    -0.72
     BET
    -0.72
    POSITIVE LOGITS
    12
    1.28
     12
    1.10
     1280
    0.99
    124
    0.99
     XII
    0.98
    126
    0.96
    123
    0.95
    122
    0.95
    elve
    0.92
     Twelve
    0.91
    Activations Density 0.512%

    No Known Activations