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. 20484
    Prev
    Next
    INDEX
    Explanations

    descriptions of scientific studies and experiments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to research studies and experiments

    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
    ANC
    -0.71
    REF
    -0.69
    ~~~~~~~~
    -0.68
    Capital
    -0.66
    dyl
    -0.65
     symbol
    -0.65
    ãĥķãĤ©
    -0.65
     regrets
    -0.63
     trump
    -0.62
     Gork
    -0.62
    POSITIVE LOGITS
     randomized
    1.02
    otype
    0.99
     samples
    0.99
     volunteers
    0.92
     Participants
    0.91
    sample
    0.91
     participants
    0.91
     study
    0.90
     sample
    0.90
     Experiment
    0.90
    Activations Density 0.784%

    No Known Activations