© 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. 11-RES-JB
    11. 10237
    Prev
    Next
    INDEX
    Explanations

    words related to intentions or meanings

    oai_token-act-pair · gpt-3.5-turbo

    the word "mean" and its various forms, focusing on expressions of intent and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aqu
    -0.72
    Newsletter
    -0.69
    icht
    -0.65
    @#&
    -0.65
    dfx
    -0.63
    ttes
    -0.62
    Sham
    -0.61
     Frazier
    -0.60
    ngth
    -0.59
    anon
    -0.58
    POSITIVE LOGITS
     spirited
    0.86
     goodbye
    0.84
    lessness
    0.75
     nothing
    0.73
     something
    0.73
    INESS
    0.72
    ãĥĥãĤ¯
    0.72
     exactly
    0.71
    erella
    0.71
     bye
    0.70
    Activations Density 0.050%

    No Known Activations