© 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. 10-RES-JB
    11. 11498
    Prev
    Next
    INDEX
    Explanations

    phrases related to introspection or reflection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "look" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accompan
    -0.70
    icipated
    -0.61
     unfocusedRange
    -0.61
     Palestin
    -0.60
    ä¹
    -0.60
    shown
    -0.59
     collaps
    -0.58
    estern
    -0.57
    uala
    -0.57
    weather
    -0.57
    POSITIVE LOGITS
     favorably
    0.86
     forward
    0.80
    ahead
    0.77
     inward
    0.76
     elsewhere
    0.76
     upon
    0.76
     toward
    0.75
     foolish
    0.74
     backward
    0.73
     kindly
    0.72
    Activations Density 0.050%

    No Known Activations