© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5759
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases and references to situations or events where clarity or understanding is lacking

    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
    36
    +0.09
    0.4%
    535
    +0.09
    0.4%
    577
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    542
    +0.09
    0.03
    271
    +0.09
    0.02
    685
    +0.09
    0.02
    Negative Logits
     Parables
    -0.66
    letters
    -0.65
    ĵ
    -0.65
    ritical
    -0.64
    fail
    -0.63
    ilts
    -0.62
    geons
    -0.62
    grand
    -0.62
    engu
    -0.58
    claimer
    -0.58
    POSITIVE LOGITS
     inside
    1.05
     behind
    1.03
     elsewhere
    0.96
     underneath
    0.92
    inside
    0.88
     beneath
    0.88
     unfolding
    0.87
     backstage
    0.87
     upstairs
    0.84
     around
    0.84
    Activations Density 0.155%

    No Known Activations