© 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. 32542
    Prev
    Next
    INDEX
    Explanations

    terms related to legal accusations and defamation

    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
    679
    +0.15
    0.7%
    591
    +0.12
    0.6%
    31
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.15
    0.13
    439
    +0.12
    0.08
    756
    +0.10
    0.01
    Negative Logits
     paradise
    -0.77
     Crush
    -0.74
    orthern
    -0.71
    thood
    -0.71
    Minecraft
    -0.70
    stable
    -0.68
    leneck
    -0.67
    rongh
    -0.65
     Females
    -0.64
    outhern
    -0.64
    POSITIVE LOGITS
     disclosures
    1.30
     representations
    1.24
     disclosure
    1.18
     inquiries
    1.17
     submissions
    1.16
     interpretations
    1.13
     statements
    1.11
     affidav
    1.10
     judgments
    1.08
     findings
    1.07
    Activations Density 1.937%

    No Known Activations