© 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. 0-RES-JB
    11. 601
    Prev
    Next
    INDEX
    Explanations

    references to food items commonly found in sandwiches

    oai_token-act-pair · gpt-3.5-turbo

    references to types of buns or sandwich elements

    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
    MS
    -0.76
    API
    -0.75
     Monteneg
    -0.75
    avia
    -0.71
    ader
    -0.69
    anian
    -0.69
    umenthal
    -0.68
     MF
    -0.67
    voice
    -0.67
    isher
    -0.67
    POSITIVE LOGITS
     bun
    4.01
     Bun
    2.60
     curls
    1.17
     hun
    1.15
     sho
    1.14
     bob
    1.07
     bra
    1.07
     bunk
    1.05
     bud
    1.03
     tee
    1.01
    Activations Density 0.033%

    No Known Activations