© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9561
    Prev
    Next
    INDEX
    Explanations

    time-related phrases denoting a point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with the word "Until" followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Redd
    -0.68
    âĵĺ
    -0.68
    )].
    -0.67
    Adds
    -0.67
    Es
    -0.65
    owers
    -0.64
    ItemImage
    -0.64
    æ©
    -0.63
    eny
    -0.62
    eas
    -0.60
    POSITIVE LOGITS
    ndra
    0.74
     Ago
    0.67
    unda
    0.64
     Stats
    0.61
    ments
    0.61
    tt
    0.61
     proven
    0.60
    nd
    0.60
    ilage
    0.60
    ONG
    0.59
    Activations Density 0.025%

    No Known Activations