© 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. 6-RES-JB
    11. 22643
    Prev
    Next
    INDEX
    Explanations

    years or specific time periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases that mention specific time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unch
    -0.70
    Sounds
    -0.64
    actor
    -0.62
     amulet
    -0.61
    AT
    -0.61
    dict
    -0.61
    acus
    -0.60
    ele
    -0.60
    wo
    -0.60
    etc
    -0.60
    POSITIVE LOGITS
    soever
    1.20
    upon
    0.84
    quickShipAvailable
    0.73
    abouts
    0.71
    irlf
    0.71
     faced
    0.69
     they
    0.68
     temperatures
    0.67
     transitioning
    0.63
    ipal
    0.62
    Activations Density 0.043%

    No Known Activations