© 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. 7-RES-JB
    11. 3155
    Prev
    Next
    INDEX
    Explanations

    instances of words related to dryness

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "dry."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anamo
    -0.78
    lehem
    -0.77
    schild
    -0.70
    GROUND
    -0.67
     Uran
    -0.66
     Canary
    -0.66
    eneg
    -0.66
     mast
    -0.65
     Sabha
    -0.64
    ichick
    -0.63
    POSITIVE LOGITS
    zzle
    1.35
    vable
    1.07
    pped
    1.07
    zz
    1.05
    zzy
    0.99
    quet
    0.93
    ppings
    0.92
    pping
    0.92
    ily
    0.87
    vin
    0.85
    Activations Density 0.051%

    No Known Activations