© 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. 10-RES-JB
    6. 7847
    Prev
    Next
    INDEX
    Explanations

    mentions of civil liberties organizations, specifically the American Civil Liberties Union (ACLU)

    oai_token-act-pair · gpt-3.5-turbo

    references to the American Civil Liberties Union (ACLU) and its related entities

    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
     Reincarn
    -0.75
    xit
    -0.69
     Destination
    -0.66
    PASS
    -0.65
    selection
    -0.64
     bye
    -0.61
    rule
    -0.61
    balls
    -0.60
     whisky
    -0.60
     breath
    -0.60
    POSITIVE LOGITS
     Liberties
    1.37
     ACLU
    1.07
     GOODMAN
    0.86
    IGHTS
    0.82
     attorney
    0.82
    thouse
    0.82
     liberties
    0.81
    Legal
    0.81
     attorneys
    0.79
    ervative
    0.78
    Activations Density 0.030%

    No Known Activations