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. 14600
    Prev
    Next
    INDEX
    Explanations

    company or organization names ending with an apostrophe followed by a lowercase 's'

    oai_token-act-pair · gpt-3.5-turbo

    instances of plural nouns

    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
    docker
    -0.72
    Reviewed
    -0.69
    Picture
    -0.66
    ļéĨĴ
    -0.65
     Volunte
    -0.65
    EVA
    -0.62
     Reef
    -0.62
    irtual
    -0.61
     Photograph
    -0.60
     misunder
    -0.60
    POSITIVE LOGITS
    selves
    0.86
     youngest
    0.76
     tallest
    0.75
     princip
    0.75
    pecially
    0.75
    outhern
    0.74
    alty
    0.74
    ername
    0.74
     birthplace
    0.73
    ELF
    0.72
    Activations Density 0.287%

    No Known Activations