© 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. 11-RES-JB
    11. 21660
    Prev
    Next
    INDEX
    Explanations

    occurrences of actions that trigger a sequence or response

    oai_token-act-pair · gpt-3.5-turbo

    the presence of punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocaly
    -0.72
    arse
    -0.70
    iphate
    -0.67
    OWN
    -0.66
    aha
    -0.66
    idable
    -0.64
    ¬¼
    -0.64
    Liter
    -0.64
    Meet
    -0.63
    onet
    -0.63
    POSITIVE LOGITS
     then
    1.28
    then
    1.08
     chances
    1.05
     THEN
    0.93
     however
    0.92
     it
    0.91
     they
    0.90
     there
    0.82
     whichever
    0.81
     please
    0.81
    Activations Density 0.138%

    No Known Activations