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. 1282
    Prev
    Next
    INDEX
    Explanations

    mentions of legal cases or court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and indicate the presence of certain significant events or actions

    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
    utical
    -0.65
     Reincarnated
    -0.62
    cation
    -0.61
    yt
    -0.61
     wherever
    -0.61
    ocobo
    -0.59
    orp
    -0.59
    uph
    -0.58
     endeavour
    -0.57
    aeda
    -0.57
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.83
    SPONSORED
    0.82
    ³³³³³³³³
    0.78
    ³³³³
    0.78
    ccording
    0.77
    WASHINGTON
    0.74
    ³³³
    0.72
    arta
    0.69
    DEN
    0.66
    FILE
    0.65
    Activations Density 0.507%

    No Known Activations