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. 21732
    Prev
    Next
    INDEX
    Explanations

    words related to technical elements and instructions, potentially related to a specific field or activity

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I'll" in various contexts

    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
    senal
    -0.78
     guiActiveUn
    -0.72
    cription
    -0.71
     à¨
    -0.69
    template
    -0.66
     è£ıç
    -0.66
     pane
    -0.66
    lished
    -0.65
    ItemImage
    -0.61
     smoker
    -0.61
    POSITIVE LOGITS
    uminati
    1.29
    oyd
    1.02
    inois
    1.02
    aday
    0.87
    ounge
    0.86
    icit
    0.85
    owship
    0.84
    igation
    0.83
    sburgh
    0.82
    ateral
    0.81
    Activations Density 0.021%

    No Known Activations