© 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. 17309
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Glad" and its variations

    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
    lished
    -0.70
     indo
    -0.70
     defe
    -0.66
    aeda
    -0.62
     Instruments
    -0.59
     Polo
    -0.58
    repre
    -0.58
     dexter
    -0.56
     educating
    -0.56
    ELL
    -0.55
    POSITIVE LOGITS
    imir
    1.14
    ys
    1.07
    bach
    1.00
    iol
    0.94
    ewater
    0.90
    ysc
    0.85
    well
    0.85
    isl
    0.84
    der
    0.83
     Tid
    0.80
    Activations Density 0.037%

    No Known Activations