© 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. 8-RES-JB
    11. 724
    Prev
    Next
    INDEX
    Explanations

    phrases related to being in the wrong place or time, equipment or tools, and requests for help or support

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to roles, responsibilities, and occurrences in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.70
     phased
    -0.63
     hiber
    -0.54
     goblins
    -0.54
     recl
    -0.53
     HOT
    -0.52
     spider
    -0.51
     NEO
    -0.51
     spiders
    -0.51
     referen
    -0.51
    POSITIVE LOGITS
    .?
    0.95
     respectively
    0.89
     thereof
    0.85
    !.
    0.83
     attRot
    0.79
    ;
    0.78
    âĢ¦.
    0.78
    ."
    0.75
     alike
    0.75
    !/
    0.73
    Activations Density 0.673%

    No Known Activations