© 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. 10294
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is untrue or inaccurate

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to falsehoods and inaccuracies

    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
    ofi
    -0.79
    ership
    -0.79
    incinn
    -0.78
    swing
    -0.78
    hov
    -0.76
    ingham
    -0.76
    adobe
    -0.75
    issue
    -0.73
    arya
    -0.73
    abiding
    -0.73
    POSITIVE LOGITS
     inaccur
    1.30
     inaccurate
    1.17
     untrue
    1.13
     misinformation
    1.04
     inacc
    0.99
     misrepresent
    0.99
    ãĥĨ
    0.91
     misled
    0.90
     falsehood
    0.88
     misunderstand
    0.88
    Activations Density 0.015%

    No Known Activations