© 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. 6-RES-JB
    11. 16647
    Prev
    Next
    INDEX
    Explanations

    names of TV channels and news programs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of television networks and news outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abiding
    -0.78
    cause
    -0.71
    profits
    -0.70
    acea
    -0.70
    rity
    -0.66
    aceae
    -0.65
    usercontent
    -0.64
    roo
    -0.62
    gra
    -0.60
    âĨij
    -0.59
    POSITIVE LOGITS
     briefing
    0.93
     interviewer
    0.89
     conference
    0.85
     interview
    0.81
     keynote
    0.74
     Observer
    0.73
     Tuesday
    0.72
     afternoon
    0.71
     Thursday
    0.70
     Wednesday
    0.69
    Activations Density 0.419%

    No Known Activations