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. 7-RES-JB
    6. 16823
    Prev
    Next
    INDEX
    Explanations

    proper nouns representing individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ampa
    -0.66
    ennett
    -0.65
    .>>
    -0.63
    owa
    -0.63
    rers
    -0.62
    STER
    -0.61
    lly
    -0.60
    .;
    -0.58
    omsday
    -0.58
    mens
    -0.57
    POSITIVE LOGITS
     formerly
    1.10
     originally
    1.05
     previously
    1.04
    wolves
    1.00
    hes
    1.00
     supposed
    0.95
     instrumental
    0.91
     initially
    0.89
     conceived
    0.89
     born
    0.86
    Activations Density 0.176%

    No Known Activations