© 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. 4856
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional responses or sentiments

    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
    259
    +0.12
    0.5%
    531
    +0.12
    0.5%
    702
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.12
    0.05
    531
    +0.12
    0.05
    386
    +0.12
    0.05
    Negative Logits
    icle
    -0.78
     Hawth
    -0.66
    icles
    -0.64
     sibling
    -0.62
     diaper
    -0.60
     shoe
    -0.60
     waterfall
    -0.59
     glide
    -0.58
     diapers
    -0.57
    agog
    -0.56
    POSITIVE LOGITS
    llah
    0.83
    arity
    0.76
    actionDate
    0.70
     sidx
    0.70
    """
    0.69
    etta
    0.69
     Cosponsors
    0.68
    âĢİ
    0.67
    jad
    0.67
    alities
    0.65
    Activations Density 0.358%

    No Known Activations