© 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. 10-RES-JB
    11. 10706
    Prev
    Next
    INDEX
    Explanations

    words indicating a contradiction or alternative viewpoint

    oai_token-act-pair · gpt-3.5-turbo

    contrasting phrases that introduce shifts in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meta
    -0.66
    zero
    -0.62
    ILLE
    -0.61
    pert
    -0.60
    emn
    -0.59
    imgur
    -0.57
    ogg
    -0.57
    SI
    -0.57
    coat
    -0.56
    ruit
    -0.56
    POSITIVE LOGITS
     rather
    1.90
    rather
    1.50
     instead
    1.39
     Rather
    1.31
     merely
    1.19
    Rather
    1.12
    instead
    1.07
    Instead
    1.06
     nevertheless
    1.04
     Instead
    1.02
    Activations Density 0.077%

    No Known Activations