© 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. 31720
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal ownership and rules

    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
    602
    +0.12
    0.6%
    292
    +0.11
    0.5%
    36
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.12
    0.16
    7
    +0.11
    0.13
    55
    +0.10
    0.14
    Negative Logits
    ãĤ©
    -0.79
    ĸļ
    -0.77
    hester
    -0.74
     grips
    -0.73
    itiveness
    -0.73
     Hast
    -0.71
    atl
    -0.69
     Commando
    -0.69
    ffe
    -0.68
    yss
    -0.65
    POSITIVE LOGITS
     permissible
    1.30
     eligible
    1.28
     considered
    1.25
     ineligible
    1.24
     punishable
    1.16
     disqualified
    1.16
     prohibited
    1.15
     exempt
    1.14
     exempted
    1.13
     deemed
    1.12
    Activations Density 1.178%

    No Known Activations