© 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. 9-RES-JB
    11. 2657
    Prev
    Next
    INDEX
    Explanations

    phrases starting with the word "How"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "How."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uthor
    -0.65
     exceptions
    -0.61
    volent
    -0.58
    oubted
    -0.58
    roads
    -0.56
    peak
    -0.56
     exception
    -0.56
    ceptions
    -0.55
    enance
    -0.55
     territory
    -0.55
    POSITIVE LOGITS
    itzer
    1.08
    ling
    1.04
    soever
    0.99
    ever
    0.94
    dy
    0.92
    lers
    0.91
    ells
    0.87
    itz
    0.84
    ls
    0.77
     MUCH
    0.77
    Activations Density 0.073%

    No Known Activations