© 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. 9556
    Prev
    Next
    INDEX
    Explanations

    the word "slack" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "slack" in various contexts

    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
     Gutenberg
    -0.70
    ITNESS
    -0.67
     Citizens
    -0.66
    LECT
    -0.66
     è£ıç
    -0.66
     Publishers
    -0.64
    ROR
    -0.64
     Sole
    -0.63
    >>>>>>>>
    -0.63
    ————
    -0.62
    POSITIVE LOGITS
     slack
    1.35
    uler
    1.03
    yip
    1.00
    luster
    0.94
    stem
    0.88
    icum
    0.83
    hang
    0.81
    eners
    0.81
     Slack
    0.81
    ©¶æ¥µ
    0.80
    Activations Density 0.004%

    No Known Activations