© 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. 9446
    Prev
    Next
    INDEX
    Explanations

    mentions of legal cases, investigations, conflicts, and probes in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal cases and investigations

    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
    aez
    -0.84
    ecause
    -0.68
    aiden
    -0.64
    vic
    -0.61
    \\\\\\\\
    -0.61
    urai
    -0.61
    imon
    -0.61
    EEK
    -0.60
    olson
    -0.60
    ãĥĥãĥī
    -0.59
    POSITIVE LOGITS
     Ferdinand
    0.90
     Canaver
    0.83
    osphere
    0.81
     Garry
    0.79
    iest
    0.73
    waters
    0.70
     Titanic
    0.70
     Haram
    0.69
     Rodney
    0.69
     Artemis
    0.67
    Activations Density 0.542%

    No Known Activations