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. 2776
    Prev
    Next
    INDEX
    Explanations

    names, titles, or terms related to specific entities or topics, particularly those related to media or events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities, particularly names and titles related to "Crimson" and "Barber."

    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
    oken
    -0.85
    eka
    -0.84
    hran
    -0.81
    ruck
    -0.74
    lihood
    -0.73
    lem
    -0.71
    lier
    -0.68
    ////////
    -0.68
    chn
    -0.68
    liness
    -0.66
    POSITIVE LOGITS
     Gems
    0.78
     Tide
    0.78
     Crimson
    0.76
     axes
    0.75
     Compos
    0.75
     CLR
    0.71
    aneers
    0.71
     Kirin
    0.70
     coded
    0.69
     gems
    0.69
    Activations Density 0.044%

    No Known Activations