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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 18584
    Prev
    Next
    INDEX
    Explanations

    references to projects or services

    oai_token-act-pair · gpt-3.5-turbo

    words related to projects and supporting community initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.68
     incorpor
    -0.63
     Schro
    -0.60
    itialized
    -0.60
    udos
    -0.56
    TABLE
    -0.56
     omission
    -0.54
     reconc
    -0.53
     retract
    -0.50
     explan
    -0.50
    POSITIVE LOGITS
    .
    0.88
    .</
    0.87
    *.
    0.84
    .:
    0.83
     or
    0.81
    .''.
    0.81
    .*
    0.78
     anymore
    0.77
    .''
    0.77
    _.
    0.74
    Activations Density 0.678%

    No Known Activations