© 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. 24048
    Prev
    Next
    INDEX
    Explanations

    passive voice constructions with "designed" or "written"

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, specifically the word "and."

    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
    ventus
    -0.79
    azi
    -0.75
    ļéĨĴ
    -0.73
     Picks
    -0.71
    heny
    -0.68
    itans
    -0.68
    lus
    -0.65
    inction
    -0.64
    anta
    -0.63
     Focus
    -0.63
    POSITIVE LOGITS
     tested
    1.40
     maintained
    1.39
     marketed
    1.38
     executed
    1.35
     analyzed
    1.28
     operated
    1.28
     photographed
    1.27
     financed
    1.26
     mastered
    1.26
     evaluated
    1.26
    Activations Density 0.107%

    No Known Activations