© 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. 15171
    Prev
    Next
    INDEX
    Explanations

    information related to managerial actions and employee work tasks

    oai_token-act-pair · gpt-3.5-turbo

    commas or similar punctuation marks used in the context of complex sentences

    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
    opal
    -0.70
    lust
    -0.66
    erity
    -0.64
    ":"/
    -0.64
    iku
    -0.64
    gression
    -0.63
    olitics
    -0.63
    ami
    -0.61
    aga
    -0.61
    OLOG
    -0.61
    POSITIVE LOGITS
     etc
    1.58
    etc
    1.09
     and
    0.84
     ect
    0.79
     respectively
    0.78
     plus
    0.74
     assorted
    0.72
     AND
    0.61
     et
    0.61
     vitamins
    0.59
    Activations Density 0.375%

    No Known Activations