© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20650
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "what."

    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
    onz
    -0.69
    ento
    -0.69
    robe
    -0.65
    psc
    -0.63
    charg
    -0.61
    po
    -0.61
    por
    -0.60
    interstitial
    -0.59
    bow
    -0.58
    eering
    -0.58
    POSITIVE LOGITS
    soever
    1.31
     happens
    1.28
     distinguishes
    1.23
     bothers
    1.14
     happened
    1.12
     constitutes
    1.11
     mattered
    1.11
     transpired
    1.05
     emerges
    1.01
     separates
    1.01
    Activations Density 0.072%

    No Known Activations