© 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. 2317
    Prev
    Next
    INDEX
    Explanations

    image captions in which specific terms or phrases are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    terms related to image captions and editing features

    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
    bats
    -0.80
     pestic
    -0.74
     incorpor
    -0.73
     illegitimate
    -0.69
    ĪĴ
    -0.67
    nes
    -0.64
    lli
    -0.63
     rejuven
    -0.63
    nesia
    -0.62
     unsett
    -0.61
    POSITIVE LOGITS
     toggle
    0.92
     Courtesy
    0.91
    Enlarge
    0.86
    advertisement
    0.84
     Transcript
    0.82
    illian
    0.78
    SpaceEngineers
    0.78
    toggle
    0.75
     Mehran
    0.74
     Annotations
    0.73
    Activations Density 0.005%

    No Known Activations