© 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. 1-RES-JB
    11. 18649
    Prev
    Next
    INDEX
    Explanations

    specific mentions of a particular city

    oai_token-act-pair · gpt-3.5-turbo

    references to a political campaign

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.84
     recess
    -0.73
    hiba
    -0.71
     omission
    -0.70
     stocking
    -0.69
     predis
    -0.68
    ©¶æ
    -0.68
    utenberg
    -0.67
     Flavoring
    -0.66
     incorporation
    -0.66
    POSITIVE LOGITS
    agne
    1.79
    aign
    1.63
     Champ
    1.44
    Champ
    1.16
     Champion
    0.80
    ione
    0.79
    xon
    0.76
    plain
    0.75
    zilla
    0.75
    lord
    0.74
    Activations Density 0.011%

    No Known Activations