Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20133
    Prev
    Next
    INDEX
    Explanations

    abbreviations "Ċ" at the start of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances where actions or events are emphasized or highlighted

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andowski
    -0.85
     Vegeta
    -0.69
    hower
    -0.65
     Gohan
    -0.64
    ython
    -0.63
    ugal
    -0.63
     Goku
    -0.62
     Croatian
    -0.62
    umenthal
    -0.61
    avorite
    -0.61
    POSITIVE LOGITS
    Canada
    1.36
    Ott
    1.31
     CBC
    1.30
    CBC
    1.27
     RCMP
    1.25
    Toronto
    1.22
     Qué
    1.21
     aboriginal
    1.20
    Canadian
    1.19
     Calgary
    1.19
    Activations Density 0.181%

    No Known Activations