Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5102
    Prev
    Next
    INDEX
    Explanations

    mentions of the Sabbath and bye-related expressions

    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
    649
    +0.13
    0.6%
    420
    +0.12
    0.5%
    85
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.13
    0.01
    288
    +0.12
    0.02
    444
    +0.12
    0.01
    Negative Logits
    ions
    -0.84
    iations
    -0.82
    hips
    -0.80
    itate
    -0.80
    izoph
    -0.79
    elvet
    -0.78
    ioned
    -0.77
    itating
    -0.75
    itates
    -0.75
    ting
    -0.71
    POSITIVE LOGITS
     bye
    1.28
     Bye
    1.21
    bye
    0.97
     versa
    0.81
    nesday
    0.76
    arden
    0.75
    redo
    0.72
    Week
    0.72
    ener
    0.71
    aye
    0.70
    Activations Density 0.048%

    No Known Activations