© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18214
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of events or entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nominations or categorization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blow
    -0.68
     inflammation
    -0.68
     stadiums
    -0.66
     Frost
    -0.66
     glue
    -0.65
     Arsenal
    -0.64
     breaks
    -0.64
     loopholes
    -0.63
     squeeze
    -0.62
     exercise
    -0.62
    POSITIVE LOGITS
    nom
    4.62
     nom
    1.76
     Nom
    1.71
    winning
    1.36
    winner
    1.27
    nos
    1.15
    nor
    1.09
     nominated
    1.06
    nam
    0.97
     nominate
    0.93
    Activations Density 0.012%

    No Known Activations