© 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. 16894
    Prev
    Next
    INDEX
    Explanations

    time-related expressions describing deadlines or durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time limits or deadlines

    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
    washer
    -0.73
    urable
    -0.70
    hered
    -0.66
    raped
    -0.66
    soDeliveryDate
    -0.65
    hent
    -0.63
    Leaks
    -0.61
     meant
    -0.61
    listed
    -0.61
    pie
    -0.61
    POSITIVE LOGITS
     settle
    1.13
     prepare
    1.09
     investigate
    1.09
     explore
    1.08
     negotiate
    1.05
     commute
    1.04
     accommodate
    1.03
     determine
    1.03
     compensate
    1.02
     recover
    1.01
    Activations Density 0.110%

    No Known Activations