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. 23942
    Prev
    Next
    INDEX
    Explanations

    words or parts of words containing "ew"

    oai_token-act-pair · gpt-3.5-turbo

    the word "new"

    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
     cort
    -0.71
     retri
    -0.67
    Downloadha
    -0.66
     burg
    -0.65
     unarmed
    -0.63
     apprehend
    -0.63
     thieves
    -0.63
    REDACTED
    -0.62
     administr
    -0.61
    esthetic
    -0.61
    POSITIVE LOGITS
    estern
    1.24
    atts
    0.99
    esley
    0.98
    ew
    0.97
    een
    0.96
    sburg
    0.95
    olf
    0.93
    ild
    0.92
    eeks
    0.92
    ITNESS
    0.91
    Activations Density 0.009%

    No Known Activations