© 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. 2-RES-JB
    11. 8986
    Prev
    Next
    INDEX
    Explanations

    the recurring use of the word "although."

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

    contrasting information or exceptions within a sentence or paragraph

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hal
    -0.78
    Eye
    -0.76
    lees
    -0.76
    isible
    -0.75
    enter
    -0.74
    elle
    -0.73
    ais
    -0.72
    aed
    -0.69
    ath
    -0.68
    edu
    -0.67
    POSITIVE LOGITS
    soever
    0.82
     acknowledging
    0.82
     retaining
    0.77
     conced
    0.76
     agreeing
    0.75
    chery
    0.71
     browsing
    0.70
     recogn
    0.70
     compiling
    0.70
     dating
    0.69
    Activations Density 0.022%

    No Known Activations