© 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. 10-RES-JB
    11. 22188
    Prev
    Next
    INDEX
    Explanations

    specific markings or identifiers within a text

    oai_token-act-pair · gpt-3.5-turbo

    color codes and color-focused terminology

    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
     Wen
    -0.72
     Burke
    -0.67
    ciation
    -0.66
    arten
    -0.66
    ·
    -0.65
    Sov
    -0.64
    ullivan
    -0.62
     hed
    -0.61
     maxim
    -0.61
    âĢij
    -0.61
    POSITIVE LOGITS
     #
    2.66
    #
    2.31
     +#
    1.77
     (#
    1.66
     "#
    1.61
     ##
    1.61
    .#
    1.61
     #####
    1.58
     ###
    1.53
    ##
    1.40
    Activations Density 0.044%

    No Known Activations