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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11304
    Prev
    Next
    INDEX
    Explanations

    mentions of pipelines or aqueducts

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "reduction."

    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
     Newman
    -0.69
     snapshots
    -0.65
     Shake
    -0.64
     snapshot
    -0.61
     Whats
    -0.61
     Sunday
    -0.60
     OS
    -0.59
     shake
    -0.59
     SY
    -0.58
     freeze
    -0.58
    POSITIVE LOGITS
    uct
    4.82
    uction
    2.63
    uctive
    2.27
    UCT
    2.10
    uctions
    2.08
    uctor
    1.59
    ucer
    1.58
    ucing
    1.55
    uced
    1.53
    uces
    1.33
    Activations Density 0.019%

    No Known Activations