© 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. 2-RES-JB
    11. 22128
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment or satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of pleasure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.71
    REE
    -0.69
    ept
    -0.66
    pat
    -0.64
     dotted
    -0.63
    enz
    -0.62
    arettes
    -0.62
     Noon
    -0.61
    nants
    -0.60
    ãĤ§
    -0.60
    POSITIVE LOGITS
     pleasure
    1.32
     gratification
    0.94
    obbies
    0.94
    joy
    0.90
     enjoyment
    0.89
     pleasures
    0.87
     pleas
    0.82
    iscopal
    0.78
    urous
    0.77
    ously
    0.77
    Activations Density 0.007%

    No Known Activations