© 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. 14019
    Prev
    Next
    INDEX
    Explanations

    words related to deceit or pretending

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quer" related to questioning or inquiry

    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
     rooting
    -0.62
     Feed
    -0.62
     Stern
    -0.58
     STATS
    -0.58
     Gene
    -0.58
     DRAG
    -0.58
     permitting
    -0.57
     personalized
    -0.57
     Cosponsors
    -0.57
     Ryder
    -0.57
    POSITIVE LOGITS
    quer
    1.46
    querade
    1.04
    ÃŃa
    0.95
    ading
    0.95
    ãĤ©
    0.88
    aque
    0.88
    oise
    0.88
    aders
    0.86
    ay
    0.83
    assic
    0.83
    Activations Density 0.008%

    No Known Activations