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. 6533
    Prev
    Next
    INDEX
    Explanations

    words related to poetry or poetic language, possibly including rhymes

    oai_token-act-pair · gpt-3.5-turbo

    words that contain the sound "ae"

    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
    ICK
    -0.90
    ENTION
    -0.78
    icked
    -0.71
    agers
    -0.69
    ickers
    -0.68
    AGE
    -0.68
    rooms
    -0.66
     Halls
    -0.65
     Sounders
    -0.65
     Gord
    -0.64
    POSITIVE LOGITS
    gypt
    1.11
    lect
    1.07
    ppelin
    0.96
    hler
    0.93
    lyn
    0.92
    bris
    0.91
    ppel
    0.90
    lete
    0.90
    pta
    0.89
    lda
    0.86
    Activations Density 0.012%

    No Known Activations