© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 3658
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to probabilities or frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ney
    -0.69
     Rogue
    -0.69
     Shy
    -0.68
     Vance
    -0.67
    drawn
    -0.66
    roth
    -0.66
     Ambassador
    -0.65
     Stephenson
    -0.64
     Tyler
    -0.64
     Runner
    -0.61
    POSITIVE LOGITS
    ãĤ¼
    0.86
     istg
    0.70
    ulse
    0.69
    ãĥ¯ãĥ³
    0.65
    ramid
    0.65
    secut
    0.65
    ajo
    0.64
     gallon
    0.64
     chronological
    0.63
     mascara
    0.63
    Activations Density 0.273%

    No Known Activations