© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 18394
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations and future plans

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to expectations and scheduled events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.80
     supposed
    -0.75
     gotta
    -0.71
     forgetting
    -0.67
    Avg
    -0.67
     supposedly
    -0.65
    quickShipAvailable
    -0.61
     Stupid
    -0.60
    æ©Ł
    -0.60
     Mint
    -0.59
    POSITIVE LOGITS
     tomorrow
    0.92
     sometime
    0.91
     someday
    0.88
     soon
    0.82
     anytime
    0.78
    morrow
    0.77
    omething
    0.72
     NEXT
    0.70
    ezvous
    0.69
    urther
    0.68
    Activations Density 0.396%

    No Known Activations