© 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. 4-RES-JB
    11. 4340
    Prev
    Next
    INDEX
    Explanations

    contrasting situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "although" in various contexts indicating contrast

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

    No Comments

    Negative Logits
    hal
    -0.80
    lees
    -0.79
    enter
    -0.75
    jar
    -0.75
    isible
    -0.75
    Bas
    -0.74
    ath
    -0.68
    ns
    -0.66
    yll
    -0.66
    edu
    -0.66
    POSITIVE LOGITS
     admittedly
    0.91
     preferably
    0.85
     acknowledging
    0.82
     interestingly
    0.78
     ideally
    0.74
    chery
    0.74
    soever
    0.74
    tons
    0.74
     fortunately
    0.73
     nevertheless
    0.73
    Activations Density 0.039%

    No Known Activations