© 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. 5803
    Prev
    Next
    INDEX
    Explanations

    phrases relating to things happening outside of specific locations or contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of activities or events occurring outside of defined societal or conventional boundaries

    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
    footed
    -0.72
    mist
    -0.64
    "></
    -0.62
     Sorce
    -0.61
    wo
    -0.61
    faced
    -0.61
    Next
    -0.59
    si
    -0.59
    ENCY
    -0.59
    <?
    -0.59
    POSITIVE LOGITS
     bounds
    1.22
     confines
    1.02
     borders
    0.91
     courtroom
    0.89
     boundaries
    0.88
     scope
    0.84
     usual
    0.82
     walls
    0.80
     classroom
    0.78
     courthouse
    0.75
    Activations Density 0.090%

    No Known Activations