© 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. 10-RES-JB
    11. 9309
    Prev
    Next
    INDEX
    Explanations

    complex phrases involving combinations of adverbs, verbs, and adjectives

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that suggest relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADS
    -0.74
    °
    -0.71
    orio
    -0.69
    iage
    -0.69
     Rings
    -0.68
     Bowl
    -0.68
     Releases
    -0.68
     Pastebin
    -0.64
    UFF
    -0.64
    ahime
    -0.64
    POSITIVE LOGITS
     efficiently
    1.43
     forcefully
    1.35
     violently
    1.31
     painfully
    1.27
     securely
    1.26
     decisively
    1.25
     loudly
    1.25
     cautiously
    1.25
     confidently
    1.24
    successfully
    1.24
    Activations Density 0.126%

    No Known Activations