© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 14026
    Prev
    Next
    INDEX
    Explanations

    dates and URLs within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to years and numerical data in a specific format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leaflets
    -0.63
     Shield
    -0.62
    plane
    -0.59
     Butterfly
    -0.57
     pen
    -0.57
    ciation
    -0.57
     Mellon
    -0.57
    antry
    -0.55
     Choice
    -0.55
    onite
    -0.54
    POSITIVE LOGITS
    03
    1.34
    02
    1.32
    07
    1.31
    06
    1.31
    04
    1.28
    08
    1.27
    09
    1.24
    05
    1.23
    01
    1.17
    Feb
    1.06
    Activations Density 0.028%

    No Known Activations