© 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. 422
    Prev
    Next
    INDEX
    Explanations

    the word "delicate."

    oai_token-act-pair · gpt-4-turbo

    descriptions of delicate things or procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to finesse or fragility

    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
    aze
    -0.73
    ITNESS
    -0.72
    SPONSORED
    -0.71
    ablishment
    -0.70
    hers
    -0.68
    Introduced
    -0.66
    aucas
    -0.65
     Cheong
    -0.65
    \/
    -0.65
     Gutenberg
    -0.64
    POSITIVE LOGITS
     delicate
    1.24
     sensibilities
    0.91
     delic
    0.79
     touches
    0.78
    tail
    0.76
    tons
    0.75
     breeze
    0.75
     balancing
    0.74
    ombo
    0.74
     sensitive
    0.74
    Activations Density 0.010%

    No Known Activations