© 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. 1-RES-JB
    11. 885
    Prev
    Next
    INDEX
    Explanations

    personal or last names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Hicks" and variations of "Hick" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.75
    AUT
    -0.72
    WAYS
    -0.67
    èª
    -0.65
    BILITY
    -0.65
    inent
    -0.62
    ################
    -0.62
    âĸ¬âĸ¬
    -0.61
    joined
    -0.61
    ãĥ´ãĤ¡
    -0.60
    POSITIVE LOGITS
     Hicks
    1.20
    haw
    1.11
    ilon
    1.07
     Racer
    0.91
    chell
    0.89
    hyde
    0.88
    elin
    0.84
    peed
    0.83
    ocity
    0.82
    imore
    0.81
    Activations Density 0.010%

    No Known Activations