© 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. 2-RES-JB
    11. 17823
    Prev
    Next
    INDEX
    Explanations

    references to daytime

    oai_token-act-pair · gpt-3.5-turbo

    references to times of day, particularly daytime and nighttime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ences
    -0.77
    rish
    -0.75
    LESS
    -0.74
    ontent
    -0.73
    ific
    -0.72
    abwe
    -0.72
    eria
    -0.71
    ARI
    -0.71
    uese
    -0.70
    Cola
    -0.69
    POSITIVE LOGITS
    urnal
    1.06
     daytime
    0.88
     nighttime
    0.81
     nightly
    0.77
     amen
    0.74
     renewal
    0.72
     unsus
    0.71
     occupancy
    0.71
    peed
    0.68
     skies
    0.68
    Activations Density 0.018%

    No Known Activations