© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 7056
    Prev
    Next
    INDEX
    Explanations

    entities or organizations related to finance, investment, or political groups

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizational structures and divisions within various entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canucks
    -0.67
     Bagg
    -0.66
     positives
    -0.64
     incrim
    -0.64
     Bengals
    -0.63
     pictures
    -0.63
    blank
    -0.63
     Oilers
    -0.62
     saline
    -0.62
     Episode
    -0.62
    POSITIVE LOGITS
    ariat
    0.95
    orate
    0.92
    aires
    0.85
     headquartered
    0.85
    eers
    0.83
    hement
    0.79
    itute
    0.78
     Directorate
    0.76
    orer
    0.76
     UNESCO
    0.74
    Activations Density 0.348%

    No Known Activations