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. 9-RES-JB
    6. 6234
    Prev
    Next
    INDEX
    Explanations

    names of individuals associated with a creative work, such as artists, musicians, or filmmakers

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =\"
    -0.71
     feasible
    -0.68
     existence
    -0.65
     lower
    -0.62
     endeavor
    -0.60
     existed
    -0.60
    Compat
    -0.59
     institution
    -0.58
     exist
    -0.58
    CONCLUS
    -0.57
    POSITIVE LOGITS
     Geoff
    1.12
     Jr
    1.11
     Frances
    1.09
     Stephanie
    1.08
     Geoffrey
    1.08
     Patrick
    1.08
     Raphael
    1.08
     Richie
    1.08
     Ian
    1.07
     Elise
    1.07
    Activations Density 0.166%

    No Known Activations