© 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. 1-RES-JB
    11. 24184
    Prev
    Next
    INDEX
    Explanations

    computer code syntax related to specific commands or functions

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol or term used in programming or mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uay
    -0.83
    agra
    -0.73
    cham
    -0.73
    oin
    -0.73
    vern
    -0.73
    Soc
    -0.73
    giving
    -0.72
    opher
    -0.72
    aeus
    -0.71
    ambers
    -0.71
    POSITIVE LOGITS
     âĪĴ
    1.09
     (âĪĴ
    0.91
     "$:/
    0.89
    âĪĴ
    0.84
     McGregor
    0.77
    riots
    0.71
    ially
    0.70
    vertisements
    0.68
     sher
    0.68
    bered
    0.68
    Activations Density 0.015%

    No Known Activations