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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5422
    Prev
    Next
    INDEX
    Explanations

    references to gay and homosexual identities and issues

    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
    314
    +0.13
    0.6%
    12
    +0.10
    0.5%
    420
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.13
    0.02
    57
    +0.10
    0.02
    643
    +0.09
    0.02
    Negative Logits
    âĵĺ
    -0.71
    AUT
    -0.67
    ICS
    -0.64
    PsyNetMessage
    -0.62
    è¦ļéĨĴ
    -0.62
     sidx
    -0.62
    OWS
    -0.61
    uria
    -0.61
    yrinth
    -0.60
     incent
    -0.60
    POSITIVE LOGITS
    atri
    1.09
    lord
    0.97
    ening
    0.84
    glers
    0.82
    croft
    0.78
    atorium
    0.78
    bie
    0.77
     marriage
    0.76
    bies
    0.76
    ness
    0.76
    Activations Density 0.040%

    No Known Activations