© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5526
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "appear" and its variations in the context of visibility or participation

    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
    310
    +0.11
    0.5%
    168
    +0.11
    0.5%
    541
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.11
    0.07
    469
    +0.11
    0.04
    322
    +0.10
    0.05
    Negative Logits
    SPONSORED
    -0.62
    pg
    -0.61
    ced
    -0.61
     ending
    -0.61
     compounded
    -0.59
    rw
    -0.58
    ichever
    -0.58
     whichever
    -0.57
    thening
    -0.57
    soever
    -0.56
    POSITIVE LOGITS
     onstage
    0.83
     billboards
    0.81
    vertisements
    0.71
     advertisements
    0.71
     corrid
    0.70
    enegger
    0.69
     banners
    0.69
    ographs
    0.69
    Featured
    0.67
    osponsors
    0.66
    Activations Density 0.817%

    No Known Activations