© 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. 10-RES-JB
    11. 10089
    Prev
    Next
    INDEX
    Explanations

    the word "keen," indicating a strong interest in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of eagerness or interest

    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
    channelAvailability
    -0.86
    天
    -0.71
    utical
    -0.69
    ICAN
    -0.66
    Ranked
    -0.64
    miah
    -0.63
    gdala
    -0.61
    idences
    -0.59
    ailable
    -0.58
    mbuds
    -0.58
    POSITIVE LOGITS
    ly
    1.20
    ness
    0.96
     to
    0.89
     eyed
    0.83
    footed
    0.82
    est
    0.82
    eful
    0.82
    ened
    0.79
     listeners
    0.79
     keen
    0.74
    Activations Density 0.029%

    No Known Activations