© 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 EvalsExportsinterp-engineNEWAPI 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. 4641
    Prev
    Next
    INDEX
    Explanations

    instances of being wrongfully accused or diagnosed

    oai_token-act-pair · gpt-3.5-turbo

    terms related to wrongful accusations and misdiagnoses

    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
    ysis
    -0.70
    iments
    -0.69
     Hands
    -0.68
    itarian
    -0.67
    berman
    -0.65
     Plan
    -0.65
     Cth
    -0.64
    iment
    -0.64
    ĺħ
    -0.64
    orno
    -0.63
    POSITIVE LOGITS
    ãĤ©
    0.87
     falsely
    0.81
     imprisoned
    0.81
     misled
    0.78
     repro
    0.78
     mistaken
    0.77
     accuse
    0.77
     imprison
    0.76
     inaccurate
    0.76
     inflated
    0.76
    Activations Density 0.009%

    No Known Activations