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. 7300
    Prev
    Next
    INDEX
    Explanations

    financial and management-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rankings and assessments in various contexts

    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
    nown
    -0.74
    ctuary
    -0.69
    piracy
    -0.66
    planned
    -0.66
    hip
    -0.62
    icable
    -0.61
    region
    -0.61
     Else
    -0.61
    agate
    -0.60
    frac
    -0.60
    POSITIVE LOGITS
     contestants
    1.46
     testers
    1.40
     interns
    1.36
     recipients
    1.36
     inmates
    1.36
     occupants
    1.34
     protagonists
    1.33
     dancers
    1.32
     singers
    1.31
     ambassadors
    1.30
    Activations Density 1.008%

    No Known Activations