© 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. 2-RES-JB
    11. 4343
    Prev
    Next
    INDEX
    Explanations

    mentions of physical locations, like military checkpoints and airport terminals

    oai_token-act-pair · gpt-3.5-turbo

    references to checkpoints and related security measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    morph
    -0.81
    soever
    -0.77
    MW
    -0.75
    nia
    -0.73
    mol
    -0.73
    tymology
    -0.73
    mort
    -0.73
    yss
    -0.73
    WW
    -0.72
    nian
    -0.71
    POSITIVE LOGITS
     checkpoints
    1.47
     checkpoint
    1.22
     clearance
    0.87
     Tanz
    0.86
     crossings
    0.84
     guards
    0.81
     guarding
    0.77
    ards
    0.75
    inery
    0.73
     kios
    0.72
    Activations Density 0.008%

    No Known Activations