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. 10-RES-JB
    6. 8629
    Prev
    Next
    INDEX
    Explanations

    person names from television shows and movies

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals associated with television or film productions

    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
     crumbling
    -0.80
    fail
    -0.78
    ntil
    -0.74
    problem
    -0.74
     vanishing
    -0.73
    warning
    -0.70
     failing
    -0.70
     inaction
    -0.70
     choking
    -0.70
    violent
    -0.70
    POSITIVE LOGITS
     participated
    1.29
     oversaw
    1.19
     joined
    1.17
     teamed
    1.16
     collaborated
    1.15
     joins
    1.12
     participates
    1.11
     oversees
    1.07
     toured
    1.04
     accompanies
    1.03
    Activations Density 0.414%

    No Known Activations