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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3235
    Prev
    Next
    INDEX
    Explanations

    and connect words to create phrases describing events, locations, activities or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing various forms of conjunction and descriptors indicating complexity and richness in experiences or offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.89
    imester
    -0.88
    ļéĨĴ
    -0.83
    ctor
    -0.79
    Ĥİ
    -0.79
    ajor
    -0.77
    Ws
    -0.77
    rued
    -0.76
    BIP
    -0.75
     Carney
    -0.74
    POSITIVE LOGITS
     thrilling
    1.25
     inspirational
    1.23
     unforgettable
    1.22
     surprises
    1.21
     quirky
    1.21
     exciting
    1.20
     inspiring
    1.17
     fascinating
    1.15
     colourful
    1.13
     excitement
    1.12
    Activations Density 0.254%

    No Known Activations