© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 19444
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific time period, often referring to a specific time of year

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a reference to "time of year."

    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
    Enlarge
    -0.78
    fml
    -0.75
    Ô
    -0.75
    berus
    -0.73
    Factor
    -0.71
     sshd
    -0.70
    netic
    -0.69
    apons
    -0.69
    krit
    -0.69
    plane
    -0.69
    POSITIVE LOGITS
     reckoning
    1.04
     worship
    0.80
     course
    0.80
     occurrence
    0.75
    onement
    0.75
     necessity
    0.74
     utmost
    0.73
     mourning
    0.72
     residence
    0.71
     celebration
    0.70
    Activations Density 0.094%

    No Known Activations