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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 11941
    Prev
    Next
    INDEX
    Explanations

    adverbs that emphasize or intensify the action described

    oai_token-act-pair · gpt-3.5-turbo

    the word "practically" and its various contexts of usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    will
    -0.76
    agate
    -0.74
    rive
    -0.71
    ictions
    -0.70
     Gate
    -0.69
    river
    -0.67
    apego
    -0.66
     Cly
    -0.66
     Flight
    -0.65
    sche
    -0.65
    POSITIVE LOGITS
    thood
    0.82
    ©¶æ¥µ
    0.80
    etheless
    0.79
    ciating
    0.78
    earchers
    0.76
     ali
    0.72
    Buyable
    0.72
     occas
    0.72
     unemploy
    0.70
     speaking
    0.69
    Activations Density 0.002%

    No Known Activations