© 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. 7-RES-JB
    11. 2157
    Prev
    Next
    INDEX
    Explanations

    dates in the format Month Year which are written as numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations of dates or periods in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oute
    -0.65
    itaire
    -0.64
     negotiators
    -0.63
     Appl
    -0.63
    iencies
    -0.63
    osponsors
    -0.61
    Interstitial
    -0.60
    plin
    -0.58
    Dialogue
    -0.58
     belts
    -0.58
    POSITIVE LOGITS
    )</
    0.73
    )/
    0.73
    %)
    0.71
    )
    0.70
    );
    0.64
    )"
    0.62
    ')
    0.61
    ]=
    0.59
    apest
    0.59
    ):
    0.58
    Activations Density 0.063%

    No Known Activations