© 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. 16095
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activities or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to actions involving handling or transferring items

    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
    _.
    -0.86
     etc
    -0.74
    ?".
    -0.69
    .*
    -0.69
    *.
    -0.68
    +.
    -0.66
    /,
    -0.65
    %.
    -0.64
    .?
    -0.64
     itself
    -0.63
    POSITIVE LOGITS
     applause
    0.83
     stret
    0.74
     congratulations
    0.74
     composure
    0.69
     unbeaten
    0.67
     fumble
    0.66
     touchdown
    0.66
     arra
    0.64
     stitches
    0.64
     cheers
    0.63
    Activations Density 0.748%

    No Known Activations