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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20203
    Prev
    Next
    INDEX
    Explanations

    instances of words related to deception or falsehood

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs

    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
    DNA
    -0.76
    arta
    -0.75
    illin
    -0.68
    wcsstore
    -0.67
    Introduced
    -0.67
    soDeliveryDate
    -0.67
    metic
    -0.64
    OUNT
    -0.63
    ŃĶ
    -0.63
    thur
    -0.62
    POSITIVE LOGITS
    ied
    0.97
    IED
    0.83
    CLASSIFIED
    0.77
     Franch
    0.74
    imentary
    0.72
    gments
    0.70
     Io
    0.70
    wic
    0.70
    ying
    0.69
    inois
    0.68
    Activations Density 0.009%

    No Known Activations