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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 3775
    Prev
    Next
    INDEX
    Explanations

    references to security checkpoints

    oai_token-act-pair · gpt-3.5-turbo

    references to checkpoints and related concepts in a discussion about movement and barriers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    morph
    -0.86
    MW
    -0.75
    Scient
    -0.75
    EMA
    -0.75
    WW
    -0.75
    nian
    -0.73
    mol
    -0.70
    yss
    -0.70
    nia
    -0.70
    tymology
    -0.70
    POSITIVE LOGITS
     checkpoints
    1.64
     checkpoint
    1.27
     Tanz
    0.85
     guards
    0.80
    inery
    0.79
     clearance
    0.77
     crossings
    0.77
     gate
    0.74
    inelli
    0.74
    andowski
    0.74
    Activations Density 0.009%

    No Known Activations