© 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. 10249
    Prev
    Next
    INDEX
    Explanations

    dialogue segments and direct quotes with a variety of speakers

    oai_token-act-pair · gpt-3.5-turbo

    instances of direct speech or quotations in the text

    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
    Offline
    -0.72
    ahime
    -0.60
     AAA
    -0.60
    cial
    -0.60
     Kinnikuman
    -0.59
    busters
    -0.59
    college
    -0.59
     Ribbon
    -0.56
    »
    -0.56
     Ct
    -0.55
    POSITIVE LOGITS
     added
    1.46
     continued
    1.44
     elaborated
    1.35
     adds
    1.25
     further
    1.20
     continues
    1.17
     proceeded
    1.16
     echoed
    1.11
     paused
    1.10
     furthermore
    1.09
    Activations Density 0.323%

    No Known Activations