© 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. 20968
    Prev
    Next
    INDEX
    Explanations

    words related to physical or emotional distress

    oai_token-act-pair · gpt-3.5-turbo

    terms related to feelings of anxiety or nervousness

    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
    noon
    -0.75
    çīĪ
    -0.74
     PubMed
    -0.67
    ALD
    -0.67
    TRY
    -0.63
    Explore
    -0.63
    TERN
    -0.63
    nit
    -0.63
    WARD
    -0.63
    lights
    -0.62
    POSITIVE LOGITS
    angu
    0.96
    pload
    0.87
    inces
    0.86
    inant
    0.84
    inary
    0.82
    pta
    0.81
    ingu
    0.80
    ille
    0.79
    ilus
    0.78
    inis
    0.78
    Activations Density 0.015%

    No Known Activations