© 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. 10384
    Prev
    Next
    INDEX
    Explanations

    terms related to data input and processing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "input" and its related context in the text

    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
     Nguyen
    -0.70
     Mub
    -0.67
     perspect
    -0.65
    llan
    -0.64
    astern
    -0.64
     Seraph
    -0.63
     Apart
    -0.62
     Nau
    -0.61
     Peninsula
    -0.61
     Colon
    -0.60
    POSITIVE LOGITS
    ting
    1.14
    ted
    1.14
    ters
    0.93
     inputs
    0.87
     input
    0.81
    Device
    0.78
    ibles
    0.75
     validation
    0.75
    raw
    0.74
    enza
    0.73
    Activations Density 0.033%

    No Known Activations