© 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. 8-RES-JB
    11. 14516
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call for change or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of limits or the end of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-
    -0.73
    ĺħ
    -0.72
    cius
    -0.72
    issance
    -0.71
    ĪĴ
    -0.71
    irez
    -0.70
    BIT
    -0.69
    hare
    -0.69
    yip
    -0.68
    omnia
    -0.66
    POSITIVE LOGITS
     than
    0.91
     nor
    0.80
     ado
    0.78
     whatsoever
    0.74
     excuses
    0.71
     usable
    0.68
    Fake
    0.67
    trace
    0.67
     pancakes
    0.67
     discriminating
    0.63
    Activations Density 0.047%

    No Known Activations