© 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. 9-RES-JB
    11. 16231
    Prev
    Next
    INDEX
    Explanations

    time-related phrases and schedules

    oai_token-act-pair · gpt-3.5-turbo

    structured time-related information, likely pertaining to schedules or event listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gra
    -0.69
     HS
    -0.66
     HF
    -0.64
     Rein
    -0.62
    ected
    -0.61
     DES
    -0.61
     Berger
    -0.60
     è£ıè
    -0.60
     HA
    -0.59
     Roose
    -0.57
    POSITIVE LOGITS
    pm
    0.77
    poon
    0.77
    itto
    0.75
    cm
    0.74
    m
    0.73
    umar
    0.72
     apiece
    0.71
     noon
    0.70
    ctl
    0.70
    mit
    0.68
    Activations Density 0.048%

    No Known Activations