© 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. 4751
    Prev
    Next
    INDEX
    Explanations

    the word "about" and its variations in various contexts

    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
    393
    +0.14
    0.7%
    608
    +0.14
    0.6%
    155
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.14
    0.07
    669
    +0.14
    0.06
    608
    +0.12
    0.07
    Negative Logits
    OGR
    -0.89
    hesis
    -0.85
    KC
    -0.83
    quez
    -0.82
    chnology
    -0.80
    rift
    -0.79
    terness
    -0.77
    ngth
    -0.76
    inen
    -0.74
    nis
    -0.73
    POSITIVE LOGITS
     how
    0.94
     whether
    0.85
     improving
    0.84
     reforming
    0.84
     obtaining
    0.83
     achieving
    0.82
     getting
    0.81
     preserving
    0.81
     committing
    0.81
     creating
    0.81
    Activations Density 0.250%

    No Known Activations