© 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. 10-RES-JB
    11. 12345
    Prev
    Next
    INDEX
    Explanations

    variables and programming terms related to coding

    oai_token-act-pair · gpt-3.5-turbo

    capital letters and abbreviations

    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
     Mongo
    -0.64
     tatt
    -0.59
    naissance
    -0.59
     Monsanto
    -0.58
     encyclopedia
    -0.56
    guards
    -0.56
     Bib
    -0.56
     Pump
    -0.56
     diapers
    -0.56
    has
    -0.56
    POSITIVE LOGITS
    -.
    1.01
    )=(
    0.99
    OTO
    0.98
    UE
    0.95
    RL
    0.94
    +
    0.93
    +.
    0.93
    ECK
    0.92
    OUR
    0.91
    NE
    0.89
    Activations Density 0.144%

    No Known Activations