© 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. 10-RES-JB
    11. 2274
    Prev
    Next
    INDEX
    Explanations

    abnormal characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    references to specific technologies and their impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reloaded
    -0.68
     Engel
    -0.63
     crucifix
    -0.60
     handshake
    -0.56
     Hats
    -0.56
     Rw
    -0.56
     pestic
    -0.55
    åį
    -0.55
    çĭ
    -0.55
     redesign
    -0.54
    POSITIVE LOGITS
    tile
    0.80
    cific
    0.79
    nesota
    0.78
    tis
    0.77
    tal
    0.77
    tions
    0.76
    si
    0.76
    lar
    0.76
    ti
    0.75
    tion
    0.74
    Activations Density 0.010%

    No Known Activations