© 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 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. 10-RES-JB
    11. 16942
    Prev
    Next
    INDEX
    Explanations

    informational phrases related to reading policies or terms

    oai_token-act-pair · gpt-3.5-turbo

    references to reading and privacy policies

    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
    tons
    -0.66
    alogue
    -0.65
    rehend
    -0.64
    ushed
    -0.61
    road
    -0.58
     Sabha
    -0.58
    ascal
    -0.55
    creen
    -0.55
    aturated
    -0.52
     inval
    -0.52
    POSITIVE LOGITS
    ggies
    0.68
    terms
    0.68
    ARI
    0.61
    Interstitial
    0.60
    iencies
    0.60
    corruption
    0.56
    occup
    0.56
    ometimes
    0.56
    iquette
    0.56
    ãĥ³ãĤ¸
    0.54
    Activations Density 0.050%

    No Known Activations