© 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. 5253
    Prev
    Next
    INDEX
    Explanations

    geographical and demographic references related to regions and communities

    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
    436
    +0.11
    0.5%
    488
    +0.11
    0.5%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.11
    0.11
    436
    +0.11
    0.06
    420
    +0.10
    0.08
    Negative Logits
     violation
    -0.74
     pedals
    -0.69
     manuals
    -0.69
    xual
    -0.67
    ipers
    -0.67
     misuse
    -0.66
     liability
    -0.66
     deception
    -0.65
     treadmill
    -0.65
     refunds
    -0.65
    POSITIVE LOGITS
    population
    1.29
     populous
    0.97
     bordering
    0.96
     birthplace
    0.95
     sandwic
    0.93
     borders
    0.91
     fertile
    0.91
     annexed
    0.89
     neighbouring
    0.89
     situated
    0.88
    Activations Density 2.047%

    No Known Activations