© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 1074
    Prev
    Next
    INDEX
    Explanations

    phrases related to building a startup

    oai_token-act-pair · gpt-3.5-turbo

    recurring symbols or characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oven
    -0.73
    eering
    -0.72
     nuts
    -0.71
     indemn
    -0.69
     Lumpur
    -0.69
     redress
    -0.68
     palm
    -0.64
     chips
    -0.64
     shelf
    -0.64
     nut
    -0.63
    POSITIVE LOGITS
    meaning
    1.14
    feat
    1.12
    along
    1.11
    advertisement
    1.10
    among
    1.10
    which
    1.08
    these
    1.08
    perhaps
    1.07
    that
    1.06
    particularly
    1.06
    Activations Density 0.059%

    No Known Activations