© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26556
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions, lawsuits, or court-related terms

    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
    373
    +0.11
    0.5%
    104
    +0.10
    0.5%
    43
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.11
    0.09
    148
    +0.10
    0.09
    572
    +0.09
    0.08
    Negative Logits
    merga
    -0.77
     congr
    -0.75
    anyahu
    -0.74
    oled
    -0.74
    agall
    -0.73
    isSpecialOrderable
    -0.72
     cautiously
    -0.71
    ahime
    -0.71
    uggest
    -0.71
     mull
    -0.71
    POSITIVE LOGITS
     alleging
    1.07
     Defendants
    1.01
     plaintiffs
    1.01
     misrepresent
    0.98
     plaintiff
    0.98
     alleges
    0.98
     wrongful
    0.97
     alleged
    0.96
     Plaint
    0.93
     defamation
    0.92
    Activations Density 3.163%

    No Known Activations