© 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. 8-RES_POST_32K-OAI
    11. 5696
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific dates and events

    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
    314
    +0.13
    0.6%
    483
    +0.10
    0.4%
    145
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.08
    314
    +0.10
    -0.01
    232
    +0.10
    0.09
    Negative Logits
     friction
    -0.87
     removable
    -0.78
     centrif
    -0.78
     lett
    -0.75
     tread
    -0.70
     mould
    -0.69
     displ
    -0.68
     imped
    -0.68
     despised
    -0.67
     topp
    -0.67
    POSITIVE LOGITS
    Reviewer
    1.11
     Announce
    0.85
     UPDATE
    0.83
    arij
    0.80
    ername
    0.78
    isode
    0.76
    isoft
    0.75
    Update
    0.74
    update
    0.74
     GROUP
    0.73
    Activations Density 1.744%

    No Known Activations