© 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. 0-RES-JB
    11. 4188
    Prev
    Next
    INDEX
    Explanations

    words related to devoting or dedicating time or resources to a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dev" and its variations, indicating a focus on development or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hof
    -0.77
     aspirin
    -0.73
     Bayer
    -0.73
     BOX
    -0.71
     Condition
    -0.71
    lees
    -0.70
    thumbnails
    -0.68
    istle
    -0.68
    Condition
    -0.68
    meric
    -0.68
    POSITIVE LOGITS
     dev
    3.77
    dev
    2.12
     Dev
    1.92
    Dev
    1.88
    DEV
    1.65
     devs
    1.37
     rev
    1.10
     deviation
    1.05
    develop
    1.04
     rend
    1.02
    Activations Density 0.028%

    No Known Activations