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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 22892
    Prev
    Next
    INDEX
    Explanations

    phrases denoting a source or cause of an event or decision

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss decisions or opinions regarding political or 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
     resil
    -0.78
    perture
    -0.74
    chwitz
    -0.64
     respir
    -0.63
    edge
    -0.63
    é¾įåĸļ士
    -0.62
     additive
    -0.61
    ÅĤ
    -0.60
     recess
    -0.60
     Crate
    -0.60
    POSITIVE LOGITS
    Ĭ±
    0.76
    dullah
    0.75
     Saud
    0.70
     bellig
    0.70
    verend
    0.70
    Barn
    0.66
     conscience
    0.64
    TextColor
    0.62
     referees
    0.61
     Senators
    0.61
    Activations Density 0.209%

    No Known Activations