© 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 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. 5961
    Prev
    Next
    INDEX
    Explanations

    phrases related to illness or discomfort

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "sick" in various contexts

    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
    adr
    -0.73
    ailable
    -0.71
    AUT
    -0.68
    RFC
    -0.65
    ETHOD
    -0.64
    å°Ĩ
    -0.63
    successful
    -0.63
     Unch
    -0.62
    aders
    -0.61
     laund
    -0.61
    POSITIVE LOGITS
    ening
    1.10
    bay
    1.04
    ened
    1.02
    nesses
    0.99
    ness
    0.84
    est
    0.80
    etts
    0.77
    igue
    0.77
    arus
    0.76
    le
    0.74
    Activations Density 0.008%

    No Known Activations