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. 11-RES-JB
    6. 10749
    Prev
    Next
    INDEX
    Explanations

    articles with a specific formatting, specifically with the character '/' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of slashes used in citation or source notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favour
    -0.72
     boun
    -0.69
     hinge
    -0.68
     repe
    -0.68
     subp
    -0.66
     clam
    -0.66
     pronoun
    -0.65
     tongues
    -0.63
     clitor
    -0.63
     demol
    -0.62
    POSITIVE LOGITS
    AFP
    1.40
    Reuters
    1.36
    Getty
    1.35
    Bloomberg
    1.34
    Associated
    1.32
    Flickr
    1.26
    CBC
    1.23
    EPA
    1.23
    European
    1.20
    NPR
    1.19
    Activations Density 0.026%

    No Known Activations