© 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. 4-RES-JB
    11. 13403
    Prev
    Next
    INDEX
    Explanations

    descriptions or actions related to quick observation or assessment

    oai_token-act-pair · gpt-3.5-turbo

    references to "glance" or related expressions of quick observation

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

    No Comments

    Negative Logits
    âĹ¼
    -0.84
    CENT
    -0.75
    Tube
    -0.69
    unic
    -0.69
    ricular
    -0.67
    rss
    -0.67
    cel
    -0.66
    Merit
    -0.64
    contract
    -0.64
    erto
    -0.63
    POSITIVE LOGITS
     glance
    1.15
     glances
    0.87
     quizz
    0.82
    lessly
    0.78
     afar
    0.77
     Takeru
    0.77
    seeing
    0.76
     inquire
    0.76
    ahead
    0.72
    tesy
    0.71
    Activations Density 0.015%

    No Known Activations