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. 2091
    Prev
    Next
    INDEX
    Explanations

    instances where a double dash "--" is used within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    repeated dashes or hyphens used for separation or emphasis in the text

    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
    ĵĺ
    -0.75
    oshop
    -0.71
    ysis
    -0.71
     butterflies
    -0.69
     protective
    -0.68
     drain
    -0.68
     cons
    -0.67
     basil
    -0.67
    rons
    -0.66
     lifes
    -0.66
    POSITIVE LOGITS
    _-
    0.99
    âĸº
    0.76
    gpu
    0.76
    yes
    0.74
    [[
    0.73
    feat
    0.73
    ->
    0.72
    avanaugh
    0.72
    BUT
    0.72
    enable
    0.71
    Activations Density 0.034%

    No Known Activations