© 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. 21044
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a contrast or exception in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize a lack of significance or diminishment of an idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ividual
    -0.89
    entric
    -0.82
    agate
    -0.79
    ulative
    -0.72
    consumer
    -0.72
    spin
    -0.71
    CU
    -0.70
    aryl
    -0.69
    uctor
    -0.68
    alez
    -0.68
    POSITIVE LOGITS
     distinguish
    0.78
     percept
    0.78
    Ń·
    0.77
    icable
    0.77
     incons
    0.76
     insignificant
    0.72
     unnoticed
    0.72
    withstanding
    0.70
     surpr
    0.69
     noticeable
    0.69
    Activations Density 0.004%

    No Known Activations