© 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. 9-RES-JB
    11. 4222
    Prev
    Next
    INDEX
    Explanations

    contradictory statements or contrasting ideas

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meta
    -0.66
    coat
    -0.65
    zero
    -0.65
    asks
    -0.61
    nat
    -0.60
    emn
    -0.59
    ILLE
    -0.58
    und
    -0.58
    unc
    -0.58
    ory
    -0.58
    POSITIVE LOGITS
     rather
    1.71
    rather
    1.39
     instead
    1.22
     Rather
    1.20
     merely
    1.08
     nevertheless
    1.07
     nonetheless
    1.01
    Rather
    1.00
     suffice
    0.97
    Instead
    0.96
    Activations Density 0.085%

    No Known Activations