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. 0-RES-JB
    6. 9282
    Prev
    Next
    INDEX
    Explanations

    phrases related to news headlines or articles

    oai_token-act-pair · gpt-3.5-turbo

    the word "Fl" followed by various suffixes in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     posit
    -0.78
     cert
    -0.69
     bargain
    -0.68
     SAM
    -0.66
     normative
    -0.65
     serum
    -0.65
     journals
    -0.64
     Kinect
    -0.63
     ser
    -0.63
     passport
    -0.63
    POSITIVE LOGITS
    Fl
    3.60
    fl
    2.14
     Fl
    1.92
    FL
    1.70
    Flo
    1.58
     Flan
    1.50
     Flake
    1.43
    Flor
    1.37
     FL
    1.36
     Flare
    1.34
    Activations Density 0.022%

    No Known Activations