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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-RES-JB
    6. 14625
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Sig" (potentially short for Sigourney)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Sig" and its variants, likely referencing a specific entity or concept related to the context

    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
     Cassidy
    -0.69
     McH
    -0.68
     GOODMAN
    -0.62
     OK
    -0.62
     TTC
    -0.62
     school
    -0.60
     Lebanese
    -0.60
     childcare
    -0.60
     Akron
    -0.59
    ģĸ
    -0.59
    POSITIVE LOGITS
     Sig
    1.16
    ldom
    1.02
    wered
    0.92
    urd
    0.92
    uler
    0.88
    sson
    0.85
    ram
    0.81
    ourney
    0.81
    gers
    0.81
    uel
    0.81
    Activations Density 0.010%

    No Known Activations