© 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. 8-RES-JB
    11. 17711
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and penalties

    oai_token-act-pair · gpt-3.5-turbo

    key events or situations that may lead to significant consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Firstly
    -0.92
    intent
    -0.79
    irtual
    -0.75
    icip
    -0.74
    Login
    -0.73
    EStreamFrame
    -0.73
    Node
    -0.73
    omorphic
    -0.71
    dayName
    -0.71
    untu
    -0.71
    POSITIVE LOGITS
     Nixon
    1.10
     Reagan
    1.08
     Eisenhower
    1.06
     1976
    1.04
     1938
    1.03
     1968
    1.02
     postwar
    1.02
     1953
    1.02
     Watergate
    1.02
     1946
    1.00
    Activations Density 1.455%

    No Known Activations