© 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. 11-RES-JB
    11. 11090
    Prev
    Next
    INDEX
    Explanations

    specific periods of time identified by certain months or years

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases indicating the duration of events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.87
    alogy
    -0.86
    ãĥ¼ãĤ¯
    -0.84
    ascript
    -0.73
    Ble
    -0.70
    aez
    -0.69
    amus
    -0.69
    ansk
    -0.69
    alog
    -0.68
    KNOWN
    -0.68
    POSITIVE LOGITS
     January
    1.25
     April
    1.22
     September
    1.22
     October
    1.21
     February
    1.19
     November
    1.17
     June
    1.17
     December
    1.17
     July
    1.15
     August
    1.13
    Activations Density 0.117%

    No Known Activations