© 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. 17729
    Prev
    Next
    INDEX
    Explanations

    words related to legal or justice-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to significant events or issues in societal contexts

    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
     impulse
    -0.73
     whine
    -0.68
     hump
    -0.66
    HOME
    -0.65
     obstruction
    -0.64
     choir
    -0.61
     slump
    -0.60
    avorite
    -0.59
    clerosis
    -0.58
    cube
    -0.57
    POSITIVE LOGITS
    ented
    1.11
    marked
    1.09
    inged
    1.07
    oused
    1.05
    icating
    1.02
    itled
    1.01
    ared
    1.01
    athed
    1.00
    atered
    0.99
    osed
    0.99
    Activations Density 0.236%

    No Known Activations