© 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. 7-RES-JB
    11. 2083
    Prev
    Next
    INDEX
    Explanations

    mentions of press conferences

    oai_token-act-pair · gpt-3.5-turbo

    references to press conferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ju
    -0.66
    ecd
    -0.63
     romantic
    -0.62
    ighth
    -0.62
     antip
    -0.61
    csv
    -0.59
    interest
    -0.59
     locom
    -0.59
    osph
    -0.58
    gradient
    -0.58
    POSITIVE LOGITS
     announcing
    1.21
     convened
    1.01
     conference
    0.87
     plaza
    0.86
     Minutes
    0.83
     presided
    0.81
     podium
    0.81
     unveiling
    0.78
     held
    0.77
     attendees
    0.77
    Activations Density 0.036%

    No Known Activations