© 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. 9-RES-JB
    11. 11463
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to examples and explanations

    oai_token-act-pair · gpt-3.5-turbo

    sequences of the character 'e'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PEOPLE
    -0.58
     organisers
    -0.58
     unpre
    -0.57
     doub
    -0.57
     volumes
    -0.56
     everywhere
    -0.56
     Picture
    -0.56
     coron
    -0.56
     Banner
    -0.55
     sway
    -0.55
    POSITIVE LOGITS
    lements
    1.22
    lev
    1.22
    astern
    1.18
    clipse
    1.09
    gypt
    1.07
    ighth
    1.06
    uphem
    1.06
    pecially
    1.02
    ighty
    1.01
    ternally
    1.01
    Activations Density 0.018%

    No Known Activations