© 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. 10-RES_POST_32K-OAI
    11. 29615
    Prev
    Next
    INDEX
    Explanations

    references to instances of illness or dying

    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
    683
    +0.13
    0.6%
    135
    +0.12
    0.5%
    501
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.02
    374
    +0.12
    0.00
    232
    +0.12
    0.02
    Negative Logits
    EStream
    -0.70
    lished
    -0.70
    в
    -0.68
     Debor
    -0.63
    resy
    -0.61
    ccording
    -0.60
     laun
    -0.60
    Reloaded
    -0.59
     compr
    -0.59
     Bulg
    -0.58
    POSITIVE LOGITS
    espie
    1.53
    uminati
    1.33
    iard
    1.21
    iam
    1.16
    iant
    1.15
    ennial
    1.14
    inois
    1.11
    ustration
    1.09
    ows
    1.02
    animous
    1.01
    Activations Density 0.131%

    No Known Activations