© 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. 8-RES-JB
    11. 1351
    Prev
    Next
    INDEX
    Explanations

    events or actions taken by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or events involving banks and financial conditions

    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
    ©¶æ
    -0.62
    gor
    -0.58
     ts
    -0.55
    yss
    -0.54
     Nationals
    -0.53
    idth
    -0.51
     isEnabled
    -0.49
     cz
    -0.49
     Ts
    -0.48
     teasp
    -0.48
    POSITIVE LOGITS
     accordingly
    1.38
     thereafter
    1.14
    .[
    1.00
    .
    1.00
     afterward
    0.97
     afterwards
    0.97
    .<
    0.92
    .(
    0.92
    +.
    0.88
     therein
    0.87
    Activations Density 1.577%

    No Known Activations