Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 19250
    Prev
    Next
    INDEX
    Explanations

    information related to percentage change and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to statistical or numerical data trends

    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
     bona
    -0.68
    ella
    -0.64
    radio
    -0.62
    QB
    -0.62
    ç«
    -0.61
    \<
    -0.60
    monitor
    -0.60
    tracks
    -0.59
    abilities
    -0.59
    asis
    -0.59
    POSITIVE LOGITS
    pees
    0.78
     total
    0.73
     average
    0.64
    Downloadha
    0.64
     overall
    0.63
     APPLIC
    0.63
     Orbit
    0.62
     potatoes
    0.61
    verts
    0.61
     economy
    0.60
    Activations Density 0.269%

    No Known Activations