© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5870
    Prev
    Next
    INDEX
    Explanations

    words or phrases that convey a sense of aggression or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    187
    +0.09
    0.4%
    328
    +0.09
    0.4%
    365
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.10
    271
    +0.09
    0.05
    453
    +0.09
    0.06
    Negative Logits
    anders
    -0.69
     Unch
    -0.62
     FANT
    -0.59
    REL
    -0.58
     IST
    -0.56
    conservancy
    -0.56
    ategory
    -0.55
     alive
    -0.54
     Aerospace
    -0.53
     Shutterstock
    -0.53
    POSITIVE LOGITS
    ly
    3.41
    LY
    2.27
    lys
    1.58
    liness
    1.55
    lies
    1.52
    fully
    1.50
    edly
    1.42
    ELY
    1.39
    liest
    1.37
    ley
    1.30
    Activations Density 1.090%

    No Known Activations