© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 8375
    Prev
    Next
    INDEX
    Explanations

    text in various languages and special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tent
    -0.73
     OP
    -0.72
     weed
    -0.71
     seed
    -0.71
     widow
    -0.70
     logger
    -0.70
     ED
    -0.67
     bush
    -0.66
     Op
    -0.65
     Whit
    -0.65
    POSITIVE LOGITS
    Ãł
    4.43
    á
    1.69
    án
    1.67
    è
    1.67
    Ç
    1.61
    Ãĥ
    1.59
     Ãł
    1.51
    ã
    1.51
    Ã
    1.41
    ê
    1.40
    Activations Density 0.017%

    No Known Activations