© 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. 11-RES-JB
    6. 2266
    Prev
    Next
    INDEX
    Explanations

    mentions of player performances and statistics in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "has" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enlarge
    -0.76
    send
    -0.67
    soType
    -0.66
    pine
    -0.64
    00007
    -0.63
    ribute
    -0.61
    ugu
    -0.61
    adiq
    -0.60
    Anonymous
    -0.59
    crop
    -0.59
    POSITIVE LOGITS
     been
    1.30
     undergone
    1.30
     averaged
    1.28
     struggled
    1.28
     gotten
    1.18
     scored
    1.18
     fared
    1.14
     endured
    1.11
     played
    1.10
     battled
    1.09
    Activations Density 0.115%

    No Known Activations