© 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. 6-RES-JB
    11. 13515
    Prev
    Next
    INDEX
    Explanations

    comparisons between people or objects

    oai_token-act-pair · gpt-3.5-turbo

    similes or comparisons using the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourse
    -0.83
    ESA
    -0.81
    alez
    -0.78
    arcity
    -0.77
    alt
    -0.74
    irtual
    -0.73
    inion
    -0.72
    Ö¼
    -0.72
    elt
    -0.72
    untu
    -0.72
    POSITIVE LOGITS
    lihood
    1.06
    lier
    1.01
    liest
    0.96
     crap
    0.82
     gib
    0.82
     garbage
    0.74
     trash
    0.73
     lifeless
    0.72
     yours
    0.68
     Andromeda
    0.66
    Activations Density 0.048%

    No Known Activations