© 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. 3427
    Prev
    Next
    INDEX
    Explanations

    phrases related to government agencies and policies

    oai_token-act-pair · gpt-3.5-turbo

    repetitive conjunctions and reference to immigration enforcement

    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
    ointed
    -0.72
    edly
    -0.67
    emic
    -0.63
    leys
    -0.63
    finding
    -0.63
    riber
    -0.62
    usky
    -0.62
    caps
    -0.61
    abolic
    -0.61
     ital
    -0.61
    POSITIVE LOGITS
     SpaceX
    0.69
     robotics
    0.68
    brates
    0.65
    Sensor
    0.65
     Papua
    0.65
    ãĥ¯
    0.64
     Palestine
    0.61
     Verge
    0.60
    brate
    0.60
     practition
    0.59
    Activations Density 0.161%

    No Known Activations