© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12828
    Prev
    Next
    INDEX
    Explanations

    terms related to contrast or opposition

    oai_token-act-pair · gpt-3.5-turbo

    instances of contrasting situations or circumstances

    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
    videos
    -0.82
    Area
    -0.81
    ovo
    -0.79
    ODY
    -0.75
    apon
    -0.74
    irez
    -0.74
     Travels
    -0.73
    UD
    -0.72
    icter
    -0.71
    iband
    -0.70
    POSITIVE LOGITS
     assurances
    1.37
     warnings
    1.28
     setbacks
    1.23
     caveats
    1.11
     seeming
    1.09
     pleas
    1.09
     promises
    1.07
     setback
    1.07
     valiant
    1.05
     objections
    1.05
    Activations Density 0.124%

    No Known Activations