© 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 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. 28757
    Prev
    Next
    INDEX
    Explanations

    terms related to roles, professions, or designations

    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
    174
    +0.11
    0.5%
    42
    +0.10
    0.4%
    91
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.13
    371
    +0.10
    0.08
    247
    +0.09
    0.06
    Negative Logits
    ilion
    -0.79
    اÙĦ
    -0.73
    omething
    -0.68
    earch
    -0.68
    STDOUT
    -0.68
    ilver
    -0.65
    ERO
    -0.64
    creen
    -0.64
    angan
    -0.62
    leeve
    -0.62
    POSITIVE LOGITS
    hood
    1.32
    ial
    1.19
    esses
    1.17
    dom
    1.13
    ially
    1.11
     extraord
    1.09
    ship
    1.05
    doms
    1.04
    ials
    1.03
    gery
    1.01
    Activations Density 1.605%

    No Known Activations