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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23492
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases conveying positive emotion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of admiration or critique related to music, culture, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHAT
    -0.72
    ctors
    -0.70
     Quit
    -0.70
    CAST
    -0.66
    veland
    -0.66
     Courier
    -0.65
    cius
    -0.64
    eworthy
    -0.64
     repro
    -0.63
    study
    -0.63
    POSITIVE LOGITS
     pesky
    0.69
     Horizon
    0.69
     morphed
    0.67
    ãĤ©
    0.64
     Upton
    0.63
    isphere
    0.62
     Ronaldo
    0.61
    é¾įå¥ij士
    0.60
    footed
    0.60
     Scream
    0.59
    Activations Density 0.367%

    No Known Activations