© 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. 31651
    Prev
    Next
    INDEX
    Explanations

    instances of personal achievements and roles in various contexts

    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
    364
    +0.10
    0.4%
    58
    +0.10
    0.4%
    697
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.10
    0.13
    551
    +0.10
    0.09
    86
    +0.10
    0.08
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
     twist
    -0.60
     behalf
    -0.59
    Translation
    -0.58
     resultant
    -0.58
    detail
    -0.56
     translating
    -0.55
    twitter
    -0.55
     unfolding
    -0.55
    erning
    -0.54
    POSITIVE LOGITS
     previously
    1.38
     previous
    1.29
     formerly
    1.21
     earlier
    1.18
     originally
    1.13
     predecessor
    1.02
     once
    1.02
     prior
    1.01
     predecessors
    1.00
     Previously
    0.97
    Activations Density 1.662%

    No Known Activations