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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 19772
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names of individuals or places, particularly with a pattern of starting with "Haw" or "Hab"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the name "Haw" and "Hab."

    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
    imates
    -0.76
     guiActiveUnfocused
    -0.74
    chnology
    -0.68
    ablishment
    -0.67
     negatives
    -0.66
    ependent
    -0.65
     amplification
    -0.64
    uania
    -0.64
     CLS
    -0.62
     receipts
    -0.62
    POSITIVE LOGITS
    keye
    1.12
    itating
    1.07
    itable
    1.04
    aii
    1.03
    itant
    1.03
    ity
    1.03
    itational
    1.03
    itate
    1.00
    itar
    1.00
    itability
    0.97
    Activations Density 0.059%

    No Known Activations