© 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. 6-RES-JB
    11. 2671
    Prev
    Next
    INDEX
    Explanations

    commands or instructions written in the form "XYZ reads/reads: ABC"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "read" and its variants in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ño
    -0.75
    unity
    -0.71
    apolis
    -0.69
    pload
    -0.68
    ortium
    -0.67
    avement
    -0.63
     Goodman
    -0.62
    engeance
    -0.62
    idable
    -0.62
     Territory
    -0.60
    POSITIVE LOGITS
     aloud
    1.28
    just
    1.07
    dress
    0.99
     comprehension
    0.89
    ahead
    0.87
    mitt
    0.85
    mill
    0.83
    \\\\\\\\
    0.83
    ILY
    0.82
    printed
    0.82
    Activations Density 0.029%

    No Known Activations