© 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. 7-RES-JB
    11. 12560
    Prev
    Next
    INDEX
    Explanations

    phrases related to observation or noticing

    oai_token-act-pair · gpt-3.5-turbo

    instances of "notice" and related expressions signaling observation or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uries
    -0.78
    ribes
    -0.75
    ieve
    -0.70
     certific
    -0.68
    icted
    -0.66
    aneers
    -0.63
    faith
    -0.62
    etime
    -0.62
    ribe
    -0.62
    ompl
    -0.62
    POSITIVE LOGITS
     similarity
    1.06
     similarities
    1.02
     resemblance
    0.99
     inconsistency
    0.88
     pecul
    0.84
     discrepancies
    0.82
     subtle
    0.82
     discrepancy
    0.81
     difference
    0.81
     inconsistencies
    0.80
    Activations Density 0.260%

    No Known Activations