© 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. 10-RES-JB
    11. 12738
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and keywords related to coding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to programming concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.74
     GoPro
    -0.74
    cigarette
    -0.73
    reenshot
    -0.71
    BuyableInstoreAndOnline
    -0.70
     mattress
    -0.69
    amsung
    -0.69
     Photographer
    -0.69
     Pepsi
    -0.69
     CCTV
    -0.68
    POSITIVE LOGITS
     syntax
    1.40
     Haskell
    1.35
     lambda
    1.34
     Scala
    1.27
     Functions
    1.26
     Clojure
    1.24
     tuple
    1.24
     parser
    1.24
     polymorph
    1.23
     synt
    1.23
    Activations Density 0.452%

    No Known Activations