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. 10-RES-JB
    6. 1844
    Prev
    Next
    INDEX
    Explanations

    names consisting of three letters followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and acronyms

    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
     McD
    -0.91
     Flan
    -0.82
     Azerbai
    -0.78
     ILCS
    -0.73
     Payton
    -0.72
     Shel
    -0.70
     Ashley
    -0.68
     PAL
    -0.67
     Jenna
    -0.67
     lodging
    -0.66
    POSITIVE LOGITS
    us
    1.95
    US
    1.47
    uses
    1.39
    uss
    1.30
    usk
    1.26
    rus
    1.17
    ius
    1.14
    usc
    1.10
    ust
    1.02
    usal
    1.02
    Activations Density 0.076%

    No Known Activations