Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7757
    Prev
    Next
    INDEX
    Explanations

    words related to technology and programming languages, specifically focusing on PHP and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating definitions or introductions to various topics

    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
     misplaced
    -0.76
     repl
    -0.74
     slog
    -0.74
     casualty
    -0.73
     rook
    -0.73
     resent
    -0.73
     decriminal
    -0.73
     logistical
    -0.73
     chancellor
    -0.72
     punching
    -0.72
    POSITIVE LOGITS
     Excellence
    1.46
     Names
    1.43
     Profession
    1.43
     Detail
    1.43
     Aging
    1.40
     Matter
    1.37
     Hours
    1.36
     Different
    1.34
     Yourself
    1.34
     Homeless
    1.34
    Activations Density 0.416%

    No Known Activations