© 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. 4789
    Prev
    Next
    INDEX
    Explanations

    instances of the word "know" and variations of awareness or understanding

    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
    572
    +0.12
    0.5%
    665
    +0.11
    0.5%
    590
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.12
    0.04
    242
    +0.11
    0.04
    285
    +0.11
    0.03
    Negative Logits
    oulos
    -0.81
    Dialogue
    -0.77
    Dialog
    -0.69
    ŃĶ
    -0.67
    odic
    -0.66
    attery
    -0.65
    Items
    -0.65
    oub
    -0.64
    è£ħ
    -0.64
    iment
    -0.64
    POSITIVE LOGITS
    ledge
    0.76
    hi
    0.73
    hin
    0.68
    heit
    0.68
     until
    0.67
     till
    0.67
     how
    0.63
    fulness
    0.62
    necess
    0.62
     whats
    0.62
    Activations Density 0.305%

    No Known Activations