© 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. 3307
    Prev
    Next
    INDEX
    Explanations

    similes that involve comparing something to a specific object or act

    oai_token-act-pair · gpt-3.5-turbo

    similes and metaphors using the word "like" in their comparisons

    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
    icals
    -0.80
    Access
    -0.79
    alties
    -0.77
    SPONSORED
    -0.76
     additionally
    -0.74
    abases
    -0.73
    iencies
    -0.72
    autions
    -0.72
    Rs
    -0.72
    places
    -0.72
    POSITIVE LOGITS
     sponge
    1.05
     glove
    0.99
     champ
    0.99
     hawk
    0.98
     plague
    0.93
     beacon
    0.92
     dement
    0.92
     nightmare
    0.91
     maniac
    0.91
     volcano
    0.90
    Activations Density 0.131%

    No Known Activations