© 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. 6638
    Prev
    Next
    INDEX
    Explanations

    the beginnings of sentences or sections in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce or summarize information

    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
    alties
    -0.90
    aneers
    -0.86
    ornings
    -0.84
    entimes
    -0.84
    thood
    -0.83
    ampires
    -0.82
    ãĥĺ
    -0.80
    akers
    -0.76
    gans
    -0.75
    ceans
    -0.74
    POSITIVE LOGITS
     gist
    1.21
     kicker
    1.20
     rundown
    1.16
     breakdown
    1.09
     latest
    1.07
     basics
    1.04
     list
    1.04
     backstory
    1.02
     synopsis
    1.02
     obligatory
    1.01
    Activations Density 0.082%

    No Known Activations