© 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. 9-RES-JB
    11. 13779
    Prev
    Next
    INDEX
    Explanations

    mentions of hydro-related terms, such as "hydrogeological," "hydroelectric," and "hydrocarbons."

    oai_token-act-pair · gpt-3.5-turbo

    references to hydro energy and electricity

    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
     Reward
    -0.70
    icates
    -0.66
     precincts
    -0.65
    UAL
    -0.64
    uously
    -0.64
    igator
    -0.63
     POV
    -0.62
     Lynch
    -0.61
    igators
    -0.60
     Circle
    -0.60
    POSITIVE LOGITS
    cephal
    1.44
    spective
    1.37
    static
    1.34
    active
    1.33
    spection
    1.30
    engineering
    1.25
    chemical
    1.16
    actively
    1.14
    scope
    1.13
    vert
    1.13
    Activations Density 0.058%

    No Known Activations