© 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. 9-RES-JB
    11. 3244
    Prev
    Next
    INDEX
    Explanations

    negations or contradictions within text

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases expressing denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.70
    ãĥį
    -0.67
    rift
    -0.66
    States
    -0.65
    yout
    -0.64
    ãĥIJ
    -0.64
    =(
    -0.64
    tein
    -0.61
     STATES
    -0.60
    arten
    -0.60
    POSITIVE LOGITS
     anymore
    1.10
    etheless
    1.05
    epad
    1.03
    withstanding
    1.02
    hin
    1.02
     necessarily
    0.98
     bothering
    0.90
    necess
    0.89
     kidding
    0.88
    eworthy
    0.87
    Activations Density 0.058%

    No Known Activations