© 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. 11469
    Prev
    Next
    INDEX
    Explanations

    specific words related to technical processes and equipment

    oai_token-act-pair · gpt-3.5-turbo

    negative phrasing or expressions of lack and non-compliance

    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
    kens
    -0.69
    ESE
    -0.68
    ensible
    -0.67
    strength
    -0.67
     reinstated
    -0.66
    orld
    -0.66
     largeDownload
    -0.65
     restored
    -0.65
    saf
    -0.65
    llah
    -0.65
    POSITIVE LOGITS
     wasteful
    1.10
     distractions
    1.05
     unnecessary
    0.99
     undue
    0.96
     waste
    0.96
     excessive
    0.94
     wasting
    0.94
     reliance
    0.93
     clutter
    0.91
     harmful
    0.91
    Activations Density 0.858%

    No Known Activations