© 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. 9-RES-JB
    11. 16124
    Prev
    Next
    INDEX
    Explanations

    words related to moral values and ethics

    oai_token-act-pair · gpt-3.5-turbo

    references to moral concepts and ethical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.83
    rams
    -0.70
    -+
    -0.69
     Lup
    -0.69
    nces
    -0.68
     Twice
    -0.68
    upon
    -0.67
    WER
    -0.66
    gow
    -0.65
    minster
    -0.65
    POSITIVE LOGITS
    istic
    1.15
    izing
    1.12
    ising
    1.09
     hazard
    1.03
     compass
    1.03
    ised
    1.00
     indignation
    0.99
    izational
    0.97
     equival
    0.96
    IZE
    0.95
    Activations Density 0.034%

    No Known Activations