© 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. 4191
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific medical conditions and injuries

    oai_token-act-pair · gpt-3.5-turbo

    special characters or encoding artifacts in the text

    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
    mast
    -0.75
    aband
    -0.69
    aday
    -0.67
    atra
    -0.66
    ratulations
    -0.65
    ateg
    -0.64
    ifier
    -0.63
    conservancy
    -0.63
     assembled
    -0.62
    eding
    -0.62
    POSITIVE LOGITS
    ©
    0.99
    ¢
    0.97
    HL
    0.96
    ÃĤ
    0.89
    д
    0.84
    Æ
    0.81
    ¯¯¯¯
    0.79
    Ãĥ
    0.78
    ij
    0.78
    н
    0.75
    Activations Density 0.008%

    No Known Activations