© 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. 10-RES_POST_32K-OAI
    11. 27259
    Prev
    Next
    INDEX
    Explanations

    timestamps and update notifications related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    +0.15
    0.7%
    303
    +0.12
    0.5%
    258
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.15
    0.04
    484
    +0.12
    0.03
    104
    +0.11
    0.03
    Negative Logits
    Untitled
    -0.83
    Offline
    -0.69
    inals
    -0.59
     brainstorm
    -0.58
    soDeliveryDate
    -0.57
    glomer
    -0.56
     boobs
    -0.56
    interstitial
    -0.56
     Prelude
    -0.56
    Frameworks
    -0.55
    POSITIVE LOGITS
    ]:
    1.02
     BELOW
    0.94
    !:
    0.84
     Remastered
    0.78
    oday
    0.78
    .):
    0.77
     Adds
    0.76
    :#
    0.76
    :
    0.74
    :]
    0.74
    Activations Density 0.486%

    No Known Activations