© 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. 1-RES-JB
    11. 4829
    Prev
    Next
    INDEX
    Explanations

    references to organizations or programs abbreviated with the letters "OC"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Ontario Civil Liberties Association or related organizations

    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
     Keynes
    -0.71
    things
    -0.71
     Witt
    -0.69
     Stanton
    -0.69
     Gork
    -0.67
     Michaels
    -0.66
     Kimmel
    -0.66
     Friedman
    -0.66
     Victory
    -0.65
     Wick
    -0.65
    POSITIVE LOGITS
    OC
    1.26
    ombat
    1.12
    urrencies
    1.08
    opy
    1.08
    onut
    1.06
    aml
    1.04
    urrency
    0.98
    entric
    0.96
    omb
    0.96
    abulary
    0.95
    Activations Density 0.007%

    No Known Activations