© 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. 4-RES-JB
    11. 7181
    Prev
    Next
    INDEX
    Explanations

    instances where events occur in a sequence, particularly focusing on the event happening later in that sequence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "later."

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

    No Comments

    Negative Logits
    Ble
    -0.76
    mad
    -0.71
    tick
    -0.69
    chest
    -0.68
    cking
    -0.65
    emen
    -0.63
    ickle
    -0.61
    rod
    -0.61
    Torrent
    -0.61
     Cause
    -0.60
    POSITIVE LOGITS
    etheless
    0.85
     iterations
    0.82
    noon
    0.76
     succumbed
    0.75
    aneously
    0.74
     generations
    0.74
     satell
    0.74
     succumb
    0.73
    theless
    0.73
     regretted
    0.72
    Activations Density 0.032%

    No Known Activations