© 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. 10-RES-JB
    11. 24564
    Prev
    Next
    INDEX
    Explanations

    terms related to textual content or language, particularly focusing on words and lists of words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "word" and its variations in different contexts

    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
    NetMessage
    -0.78
    etheus
    -0.72
    abama
    -0.68
     Flavoring
    -0.68
    isner
    -0.67
    cffff
    -0.67
    asio
    -0.66
    acs
    -0.65
    oute
    -0.65
    izo
    -0.63
    POSITIVE LOGITS
    press
    1.41
    sworth
    1.21
    play
    0.97
     ptr
    0.94
    mark
    0.92
     processor
    0.89
    Press
    0.86
    ifier
    0.83
     processors
    0.80
    mith
    0.79
    Activations Density 0.040%

    No Known Activations