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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17944
    Prev
    Next
    INDEX
    Explanations

    years or dates in the format "XXXX:" (e.g., 1962)

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    daq
    -0.69
     airs
    -0.65
    idan
    -0.63
    iffe
    -0.63
    igon
    -0.60
     reborn
    -0.60
    alach
    -0.59
     Brune
    -0.58
    ulent
    -0.57
    olog
    -0.56
    POSITIVE LOGITS
    DCS
    0.82
    Dear
    0.81
     '[
    0.80
     "[
    0.79
     THERE
    0.76
    ={
    0.70
    Regarding
    0.69
    Should
    0.68
     "â̦
    0.67
    atonin
    0.65
    Activations Density 0.552%

    No Known Activations