© 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. 8913
    Prev
    Next
    INDEX
    Explanations

    words related to ethical or moral involvement, such as 'complicit', 'complicity', 'knowingly', and 'acquiesced'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to involvement and accountability in unethical or illegal actions

    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
    aster
    -0.77
    aign
    -0.74
    anche
    -0.72
     Rapt
    -0.68
    oult
    -0.66
    gar
    -0.65
    eways
    -0.65
    grim
    -0.63
     Feld
    -0.62
     Krish
    -0.62
    POSITIVE LOGITS
     complicit
    1.18
     complicity
    1.02
    ãĥ¼ãĥĨãĤ£
    0.92
     wink
    0.80
    vous
    0.78
     acquies
    0.78
     unwitting
    0.78
    ãĤº
    0.78
     unknow
    0.77
    cence
    0.74
    Activations Density 0.022%

    No Known Activations