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. 10-RES-JB
    6. 11010
    Prev
    Next
    INDEX
    Explanations

    years and titles of events or establishments, particularly those related to awards or museums

    oai_token-act-pair · gpt-3.5-turbo

    instances of awards, specifically related to beauty pageants

    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
     glim
    -0.74
    Ĩ
    -0.64
     soak
    -0.63
     thous
    -0.62
     counter
    -0.61
     rooting
    -0.60
     merchant
    -0.60
     cripp
    -0.58
     Firm
    -0.57
     salty
    -0.57
    POSITIVE LOGITS
    1995
    1.81
    2006
    1.81
    1996
    1.80
    1997
    1.78
    2005
    1.78
    2004
    1.78
    2010
    1.78
    1998
    1.78
    1994
    1.77
    2008
    1.76
    Activations Density 0.072%

    No Known Activations