© 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. 4-RES-JB
    11. 10365
    Prev
    Next
    INDEX
    Explanations

    instances of the word "institute" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "institute" and its variations

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

    No Comments

    Negative Logits
    imentary
    -0.80
     Pipeline
    -0.68
    ebus
    -0.66
    EngineDebug
    -0.64
    ingham
    -0.64
    sworth
    -0.64
    loaded
    -0.64
    isexual
    -0.63
    burn
    -0.62
    WER
    -0.62
    POSITIVE LOGITS
     instit
    0.82
    ciplinary
    0.82
    itute
    0.76
    ctor
    0.75
     institute
    0.73
    pex
    0.72
    chnology
    0.71
    itutional
    0.68
    hibit
    0.67
    biz
    0.67
    Activations Density 0.014%

    No Known Activations