© 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. 1-RES-JB
    11. 24255
    Prev
    Next
    INDEX
    Explanations

    words related to expressions of strong emotions or support

    oai_token-act-pair · gpt-3.5-turbo

    mentions of outpourings of support and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Labrador
    -0.87
    dar
    -0.78
     Crown
    -0.73
     Galile
    -0.69
     Roh
    -0.66
     lodge
    -0.65
     Sul
    -0.65
     cave
    -0.64
     Rath
    -0.63
     Hab
    -0.62
    POSITIVE LOGITS
     outp
    1.33
    imates
    0.96
    issance
    0.94
     ILCS
    0.88
    acers
    0.83
    soType
    0.82
    efully
    0.80
    ributes
    0.78
    oresc
    0.77
    orescence
    0.77
    Activations Density 0.013%

    No Known Activations