© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 1552
    Prev
    Next
    INDEX
    Explanations

    references to building web applications and frameworks using different technologies such as Clojure, MongoDB, Rails, Laravel, Django, Flask, Node.js, and Express

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages and development frameworks

    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
    ocaust
    -0.81
     plaque
    -0.78
     whereabouts
    -0.73
     stricken
    -0.72
    ________________
    -0.71
     airing
    -0.70
     severed
    -0.70
     Newsweek
    -0.69
     SOLD
    -0.69
     patri
    -0.68
    POSITIVE LOGITS
     Angular
    1.56
     Clojure
    1.47
     Scala
    1.47
     JavaScript
    1.44
     Python
    1.43
     Haskell
    1.42
    Python
    1.40
     Rails
    1.40
     PHP
    1.39
     Django
    1.39
    Activations Density 1.399%

    No Known Activations