© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7976
    Prev
    Next
    INDEX
    Explanations

    terms related to legal, criminal, and investigative activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and criminal issues

    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
    htaking
    -0.66
    osate
    -0.56
    arnaev
    -0.51
    udic
    -0.51
    annabin
    -0.49
    tera
    -0.49
    arij
    -0.48
    billion
    -0.48
    arak
    -0.48
    ivan
    -0.47
    POSITIVE LOGITS
     nonetheless
    0.92
     itself
    0.90
     anyway
    0.85
     individually
    0.82
     thereafter
    0.82
     elsewhere
    0.79
     separately
    0.78
     afterward
    0.78
     themselves
    0.76
     afterwards
    0.75
    Activations Density 1.647%

    No Known Activations