© 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. 950
    Prev
    Next
    INDEX
    Explanations

    original content or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "original" and its variations

    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
    wal
    -0.78
    robe
    -0.74
    walk
    -0.72
    =-=-=-=-=-=-=-=-
    -0.71
    ega
    -0.70
    rom
    -0.68
     Simulator
    -0.67
    inging
    -0.65
    angs
    -0.65
    opping
    -0.64
    POSITIVE LOGITS
    ity
    1.05
    ITY
    1.00
     incarnation
    0.85
    itized
    0.75
     impetus
    0.74
     trilogy
    0.74
     batch
    0.73
    lly
    0.72
     poster
    0.72
    Filename
    0.71
    Activations Density 0.022%

    No Known Activations