© 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. 3-RES-JB
    11. 5085
    Prev
    Next
    INDEX
    Explanations

    words related to physical health issues or negative emotions

    oai_token-act-pair · gpt-3.5-turbo

    repetitive 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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AUT
    -0.70
    ailable
    -0.69
    adr
    -0.69
    anship
    -0.67
    ETHOD
    -0.66
    RFC
    -0.65
    izontal
    -0.64
     laund
    -0.63
    cycl
    -0.62
    ader
    -0.62
    POSITIVE LOGITS
    ening
    1.15
    bay
    1.08
    ened
    1.05
    nesses
    1.00
    ness
    0.91
    estro
    0.85
    ly
    0.78
    est
    0.78
    etts
    0.77
    le
    0.75
    Activations Density 0.010%

    No Known Activations