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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14329
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of breadth or wide-ranging topics

    oai_token-act-pair · gpt-3.5-turbo

    the term "broad" along with its variations, indicating a focus on generality or wide applicability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.74
    ILLE
    -0.70
     Keeper
    -0.67
    ICAN
    -0.67
     Bagg
    -0.66
    ngth
    -0.66
     Royale
    -0.65
    nces
    -0.65
     Gork
    -0.62
    illard
    -0.61
    POSITIVE LOGITS
    sheet
    1.60
    ening
    1.41
    sheets
    1.36
    ened
    1.23
    sword
    1.23
    side
    1.15
     spectrum
    1.13
     strokes
    1.13
    leaf
    1.09
    spread
    1.02
    Activations Density 0.030%

    No Known Activations