© 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. 5292
    Prev
    Next
    INDEX
    Explanations

    the word "to," indicating a focus on infinitive verbs and intentions

    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
    502
    +0.11
    0.5%
    665
    +0.10
    0.5%
    762
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.11
    0.16
    665
    +0.10
    0.15
    551
    +0.10
    0.14
    Negative Logits
     Plex
    -0.77
     Milky
    -0.76
     Pegasus
    -0.76
     Pixie
    -0.76
     Landing
    -0.73
     Sheet
    -0.73
     Reborn
    -0.71
     Bounty
    -0.69
     Bub
    -0.69
     Deadline
    -0.68
    POSITIVE LOGITS
     conclude
    1.23
     infer
    1.17
     envision
    1.14
     criticize
    1.10
     interpret
    1.09
     characterize
    1.08
     imagine
    1.08
     argue
    1.07
     hypothes
    1.07
     equate
    1.07
    Activations Density 0.880%

    No Known Activations