© 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. 8-RES-JB
    11. 1122
    Prev
    Next
    INDEX
    Explanations

    accusations or claims made in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" and its various repetitions indicating claims or assertions within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aukee
    -0.99
    ãĤ´ãĥ³
    -0.85
    izont
    -0.79
    alt
    -0.78
    Laughs
    -0.77
    Wide
    -0.76
    think
    -0.75
    WAYS
    -0.74
    unction
    -0.73
    inki
    -0.72
    POSITIVE LOGITS
     they
    0.90
     improper
    0.79
     inadequate
    0.78
    soever
    0.78
     improperly
    0.74
     defendants
    0.74
     he
    0.74
     faulty
    0.73
     smugglers
    0.73
     although
    0.71
    Activations Density 0.207%

    No Known Activations