© 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. 11-RES-JB
    11. 10132
    Prev
    Next
    INDEX
    Explanations

    phrases related to observation and directional language

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a viewpoint or perspective from a specific location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rition
    -0.75
    period
    -0.73
    itivity
    -0.71
    izo
    -0.66
    classic
    -0.63
    ennial
    -0.62
    atto
    -0.61
    TER
    -0.61
    wu
    -0.60
    cellent
    -0.59
    POSITIVE LOGITS
     afar
    1.82
     behind
    1.31
     rooft
    1.24
     atop
    1.24
    behind
    1.16
     beneath
    1.15
     inside
    1.14
     above
    1.14
     underneath
    1.11
     upstairs
    1.09
    Activations Density 0.108%

    No Known Activations