© 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 EvalsExportsinterp-engineNEWAPI 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. 5036
    Prev
    Next
    INDEX
    Explanations

    adjectives describing negative or unsettling characteristics

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors associated with unpleasant or eerie qualities

    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
    shire
    -0.88
    ault
    -0.88
    ainer
    -0.86
    edly
    -0.86
    hips
    -0.86
    uther
    -0.84
    inators
    -0.84
    ational
    -0.84
    ership
    -0.83
    igration
    -0.82
    POSITIVE LOGITS
     little
    0.93
    zzy
    0.83
     stuff
    0.82
     goodness
    0.79
     bits
    0.78
     dice
    0.76
     nasty
    0.71
     tid
    0.71
     bast
    0.71
     bit
    0.70
    Activations Density 0.077%

    No Known Activations