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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 10653
    Prev
    Next
    INDEX
    Explanations

    statistical or numerical information, such as numbers of appearances, assists, starts, and signings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports performance and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bicycl
    -0.74
     ZIP
    -0.71
     Cherokee
    -0.67
     nonviolent
    -0.67
     behaviors
    -0.66
    ITNESS
    -0.66
     jurisd
    -0.66
     Navajo
    -0.66
    >)
    -0.65
     FOIA
    -0.65
    POSITIVE LOGITS
     Mourinho
    1.25
     Wenger
    1.16
     Anfield
    1.14
     whilst
    1.13
     Tottenham
    1.13
     Liverpool
    1.12
     Guardiola
    1.11
     Newcastle
    1.10
     Everton
    1.09
    Liverpool
    1.09
    Activations Density 0.324%

    No Known Activations