© 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. 1-RES-JB
    11. 16430
    Prev
    Next
    INDEX
    Explanations

    references to STEM (Science, Technology, Engineering, Mathematics) fields

    oai_token-act-pair · gpt-3.5-turbo

    references to STEM (Science, Technology, Engineering, and Mathematics) fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NCT
    -0.62
     photograph
    -0.58
     dealer
    -0.58
     Ezekiel
    -0.58
    ox
    -0.57
     Franz
    -0.57
     LP
    -0.56
    Tes
    -0.56
    avis
    -0.55
     hoard
    -0.54
    POSITIVE LOGITS
     STEM
    1.18
    STEM
    1.09
    ciplinary
    0.84
    sonian
    0.81
    ONSORED
    0.81
    yip
    0.80
    pine
    0.75
    rers
    0.75
    rious
    0.74
    milo
    0.74
    Activations Density 0.016%

    No Known Activations