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

    Neuronpedia

    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. 0-RES-JB
    11. 11812
    Prev
    Next
    INDEX
    Explanations

    words related to significant events or names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lead" and its variations, indicating leadership or guidance

    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
     Panic
    -0.71
     Prism
    -0.60
     terrorists
    -0.59
     Obs
    -0.59
     upside
    -0.59
     Action
    -0.58
     torped
    -0.57
     Surprise
    -0.57
     Pros
    -0.57
     orbit
    -0.57
    POSITIVE LOGITS
    ld
    4.44
    lde
    2.28
    lder
    2.05
    lda
    1.97
    lf
    1.55
    LD
    1.54
    ldon
    1.47
    ELD
    1.38
    lt
    1.30
    ls
    1.26
    Activations Density 0.013%

    No Known Activations