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. 8224
    Prev
    Next
    INDEX
    Explanations

    instances where someone is characterized as either good or bad at something

    oai_token-act-pair · gpt-3.5-turbo

    evaluations of skills or abilities, particularly in terms of being good or bad at something

    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
    NetMessage
    -0.67
    iann
    -0.65
    ancies
    -0.65
    oya
    -0.65
    cape
    -0.63
    hea
    -0.61
    atum
    -0.61
    urrence
    -0.60
    ums
    -0.59
    omi
    -0.58
    POSITIVE LOGITS
     buddies
    0.93
    friends
    0.92
     pals
    0.88
     suited
    0.87
     friends
    0.86
     acquainted
    0.86
     negotiators
    0.85
     at
    0.85
    gered
    0.84
     defensively
    0.80
    Activations Density 0.130%

    No Known Activations