© 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. 7-RES-JB
    11. 20768
    Prev
    Next
    INDEX
    Explanations

    medical and diagnostic terms related to tests and assessments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to testing and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.88
     Confederation
    -0.85
    itol
    -0.83
     Georgian
    -0.70
    lins
    -0.63
    eworld
    -0.63
    Atl
    -0.62
    ili
    -0.61
     Anat
    -0.61
    udeau
    -0.61
    POSITIVE LOGITS
    alyses
    0.86
     evaluations
    0.86
     eval
    0.84
    undown
    0.84
     Evaluation
    0.80
     certify
    0.79
     evaluating
    0.78
     diagnostic
    0.77
     pse
    0.76
     evaluation
    0.76
    Activations Density 0.828%

    No Known Activations