© 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. 2748
    Prev
    Next
    INDEX
    Explanations

    dates in the format of month followed by year

    oai_token-act-pair · gpt-3.5-turbo

    dates and related numerical values, particularly in a chronological context

    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
     tremend
    -1.17
    ß
    -1.14
    ccording
    -1.10
    Þ
    -1.08
     oun
    -1.07
     eleph
    -1.07
    senal
    -1.03
    aditional
    -1.02
    ò
    -1.00
     exting
    -1.00
    POSITIVE LOGITS
     )
    0.65
     /*
    0.63
     NULL
    0.62
     *
    0.61
     ¶
    0.60
     ]
    0.58
     ;
    0.58
     ----------------
    0.58
     <
    0.57
     ++
    0.56
    Activations Density 0.080%

    No Known Activations