© 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. 2-RES-JB
    11. 17447
    Prev
    Next
    INDEX
    Explanations

    words related to false accusations or wrongful convictions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to wrongful accusations and false claims

    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
     Observer
    -0.75
     Hands
    -0.74
    itarian
    -0.73
    iry
    -0.69
    iment
    -0.69
    iments
    -0.67
     Presence
    -0.67
    yi
    -0.65
    igraph
    -0.65
    orno
    -0.65
    POSITIVE LOGITS
     falsely
    0.88
    ãĤ©
    0.86
     scratched
    0.84
     accuse
    0.83
     tarn
    0.81
    otom
    0.80
     wrongly
    0.78
     dissemin
    0.77
     abused
    0.76
     inaccurate
    0.76
    Activations Density 0.011%

    No Known Activations