© 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. 0-RES-JB
    11. 16859
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and concepts related to paradigms and specific people or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simmer
    -0.77
     gag
    -0.72
    vation
    -0.68
     Shane
    -0.68
    lime
    -0.67
     Scor
    -0.67
     Sunny
    -0.66
     leaked
    -0.66
     leaking
    -0.64
    burn
    -0.63
    POSITIVE LOGITS
    orf
    2.17
     paradigm
    1.68
    ijk
    1.46
     parad
    1.44
    yth
    1.41
     Mond
    1.27
     Cantor
    1.25
     pawn
    1.18
    oso
    1.10
     Parad
    1.10
    Activations Density 0.054%

    No Known Activations