© 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. 4983
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" and its variants

    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
    593
    +0.10
    0.5%
    174
    +0.10
    0.4%
    646
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.10
    0.06
    159
    +0.10
    0.06
    408
    +0.10
    0.07
    Negative Logits
    erial
    -0.70
    eming
    -0.67
    ich
    -0.64
     Quantity
    -0.64
    VID
    -0.62
    vell
    -0.61
    ablishment
    -0.60
    icals
    -0.60
    aki
    -0.60
    isan
    -0.59
    POSITIVE LOGITS
     inhib
    0.77
     misunder
    0.69
     burden
    0.69
     torch
    0.67
     burdens
    0.66
    urden
    0.65
     mantle
    0.64
     attent
    0.64
     playbook
    0.63
     hurdle
    0.63
    Activations Density 0.429%

    No Known Activations