© 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. 7829
    Prev
    Next
    INDEX
    Explanations

    actions related to decision-making and planning

    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
    41
    +0.13
    0.6%
    748
    +0.12
    0.5%
    503
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.13
    0.14
    435
    +0.12
    0.06
    665
    +0.10
    0.12
    Negative Logits
    taboola
    -0.80
    20439
    -0.74
    utm
    -0.71
    ufficient
    -0.70
     UNCLASSIFIED
    -0.69
    eeds
    -0.69
    soever
    -0.67
    orie
    -0.67
    emale
    -0.66
    sbm
    -0.65
    POSITIVE LOGITS
     ourselves
    0.93
     Spoiler
    0.82
     glim
    0.74
     myself
    0.70
     ðŁĻĤ
    0.70
     hopefully
    0.70
    Alright
    0.67
     analogy
    0.66
     sanity
    0.66
    again
    0.66
    Activations Density 5.035%

    No Known Activations