© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 10275
    Prev
    Next
    INDEX
    Explanations

    phrases related to unjust accusations or convictions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to wrongful actions or accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Observer
    -0.76
    itarian
    -0.74
    =-=-=-=-=-=-=-=-
    -0.70
    illary
    -0.70
     Authorization
    -0.69
    illin
    -0.69
     Hands
    -0.69
    iry
    -0.68
    olitan
    -0.68
    arya
    -0.68
    POSITIVE LOGITS
     falsely
    1.15
     wrongly
    0.97
     misled
    0.92
     mistakenly
    0.90
     errone
    0.87
     accuse
    0.84
     dissemin
    0.82
     fooled
    0.82
     blinded
    0.80
     scratched
    0.79
    Activations Density 0.011%

    No Known Activations