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. 291
    Prev
    Next
    INDEX
    Explanations

    text related to writing or text processing, such as "scribble", "notebook", and "keyboard"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to writing and expression

    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
    ospons
    -0.87
     Supporters
    -0.86
    LGBT
    -0.85
     LGBT
    -0.80
    osponsors
    -0.78
    soType
    -0.76
    Gay
    -0.74
    Support
    -0.74
    Season
    -0.73
    outheast
    -0.73
    POSITIVE LOGITS
     typew
    1.38
     computers
    1.20
     computer
    1.09
     diagrams
    1.08
     mathemat
    1.07
     scrib
    1.06
     PowerPoint
    1.03
    computer
    1.03
    puter
    1.02
     algorithms
    1.00
    Activations Density 1.311%

    No Known Activations