© 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. 8-RES-JB
    11. 21773
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional affiliations and career transitions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference specific teams or organizations

    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
    NetMessage
    -0.75
    rats
    -0.73
    selection
    -0.72
    agree
    -0.71
    rad
    -0.69
    Figure
    -0.69
    perse
    -0.68
    assed
    -0.68
    hari
    -0.67
    headers
    -0.67
    POSITIVE LOGITS
     same
    1.02
     aforementioned
    0.97
     Clintons
    0.96
     prestigious
    0.95
     likes
    0.95
     Department
    0.88
     United
    0.88
     highest
    0.86
     latter
    0.84
     infamous
    0.83
    Activations Density 0.278%

    No Known Activations