© 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. 2-RES-JB
    11. 12427
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or sequences of letters that may represent codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.57
     exha
    -0.53
     carbohyd
    -0.51
    Ĥİ
    -0.50
    PDATE
    -0.50
     sudden
    -0.49
     GOODMAN
    -0.48
     corrid
    -0.48
    ccording
    -0.47
     referen
    -0.47
    POSITIVE LOGITS
    ensis
    0.74
    ois
    0.62
    ragon
    0.61
    imore
    0.59
    nik
    0.58
    aux
    0.57
    aga
    0.57
    bis
    0.56
    nes
    0.55
    agi
    0.55
    Activations Density 1.549%

    No Known Activations