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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 21095
    Prev
    Next
    INDEX
    Explanations

    events or periods of time that are being referred to

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions indicating time references or historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lime
    -0.79
    erers
    -0.79
    cipl
    -0.70
    anie
    -0.70
    icidal
    -0.68
    ilver
    -0.68
    aves
    -0.66
    Īè
    -0.65
    acent
    -0.65
    amar
    -0.64
    POSITIVE LOGITS
     inception
    1.40
     beginning
    1.11
     outset
    1.06
     earliest
    1.06
     infancy
    1.01
     dawn
    1.00
     onset
    0.99
     1970
    0.93
     1990
    0.92
     1960
    0.91
    Activations Density 0.128%

    No Known Activations