© 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 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. 3-RES-JB
    11. 5727
    Prev
    Next
    INDEX
    Explanations

    mentions of academic titles or positions, particularly "Prof"entions of academic titles or positions, particularly "Prof"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of university professors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leash
    -0.75
     cruc
    -0.71
    MENTS
    -0.70
     awoken
    -0.70
    RANT
    -0.68
     ashore
    -0.66
    wolves
    -0.66
     forests
    -0.65
     queen
    -0.63
     cramped
    -0.63
    POSITIVE LOGITS
    essors
    1.60
    essor
    1.34
    iciency
    1.32
    iles
    1.19
    icient
    1.15
    ound
    1.03
    ession
    1.00
    icist
    0.93
    inction
    0.91
    ository
    0.91
    Activations Density 0.008%

    No Known Activations