© 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. 0-RES-JB
    11. 11333
    Prev
    Next
    INDEX
    Explanations

    mentions of names followed by numbers or the abbreviation 'ON'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "on."

    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
     cow
    -0.61
     Liberties
    -0.59
     eg
    -0.58
     looking
    -0.58
     refuge
    -0.58
     revenge
    -0.57
     functioning
    -0.57
     median
    -0.55
     fam
    -0.55
     shopping
    -0.55
    POSITIVE LOGITS
    ON
    3.94
    ONS
    2.72
    ons
    1.96
    ONY
    1.93
    OND
    1.88
    on
    1.76
    ONES
    1.59
    ONE
    1.58
    ONT
    1.50
    OFF
    1.45
    Activations Density 0.010%

    No Known Activations