© 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. 3204
    Prev
    Next
    INDEX
    Explanations

    words related to routes and journeys

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "aps" in various contexts

    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
    ItemImage
    -0.67
     hunger
    -0.67
    Marx
    -0.67
     Marxist
    -0.66
    ItemThumbnailImage
    -0.63
    judicial
    -0.62
     cogn
    -0.62
    BuyableInstoreAndOnline
    -0.62
     grievance
    -0.62
    \\\\\\\\\\\\\\\\
    -0.61
    POSITIVE LOGITS
    aps
    1.25
    acus
    1.08
    olicy
    1.05
    olitan
    1.01
    alm
    0.98
    ocalypse
    0.97
    olitics
    0.97
    apy
    0.95
    hemy
    0.93
    onent
    0.91
    Activations Density 0.003%

    No Known Activations