© 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. 2-RES-JB
    11. 12135
    Prev
    Next
    INDEX
    Explanations

    words related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    words or terms related to specific individuals or well-known entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    skirts
    -0.68
    FFFF
    -0.66
     gestation
    -0.65
     Winchester
    -0.64
    PDATE
    -0.63
     halves
    -0.62
    LOAD
    -0.62
     Sorceress
    -0.61
    ridges
    -0.61
     dividing
    -0.60
    POSITIVE LOGITS
    achu
    1.19
    ernels
    1.09
    istan
    1.08
    owski
    1.07
    ik
    1.03
    ernel
    0.98
    ki
    0.98
    ula
    0.96
    uli
    0.95
    ileaks
    0.95
    Activations Density 0.014%

    No Known Activations