© 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. 3-RES-JB
    11. 16130
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "retreat" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to physical locations or movements related to withdrawal or departure

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̶
    -0.74
     Collider
    -0.70
    Lev
    -0.66
    American
    -0.66
    Ô
    -0.65
    Interstitial
    -0.65
    GB
    -0.64
    Cap
    -0.64
     purse
    -0.63
    vous
    -0.62
    POSITIVE LOGITS
     retreat
    0.97
    sburg
    0.96
    icter
    0.83
    alus
    0.76
    hess
    0.75
    oleon
    0.71
    cation
    0.67
    EStream
    0.66
     confinement
    0.66
    spective
    0.65
    Activations Density 0.010%

    No Known Activations