© 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. 4-RES-JB
    11. 23704
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to fake information or news

    oai_token-act-pair · gpt-3.5-turbo

    references to "fake news"

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

    No Comments

    Negative Logits
    xual
    -0.87
    ires
    -0.75
    ands
    -0.75
    arching
    -0.73
    }}}
    -0.70
    APTER
    -0.70
    anded
    -0.69
    draw
    -0.68
    Thom
    -0.68
    azar
    -0.66
    POSITIVE LOGITS
     pas
    0.80
     fake
    0.79
    ²¾
    0.76
    ument
    0.74
     Fake
    0.72
    ãĥ¼ãĥĨãĤ£
    0.68
    eln
    0.68
    ulously
    0.67
     monster
    0.67
    outs
    0.67
    Activations Density 0.022%

    No Known Activations