© 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 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. 9-RES-JB
    11. 19654
    Prev
    Next
    INDEX
    Explanations

    phrases related to keeping up with something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to staying current or updated

    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
    »Ĵ
    -0.68
    furt
    -0.62
    ilty
    -0.60
    atis
    -0.59
     DRAG
    -0.57
    =]
    -0.55
     ACTIONS
    -0.55
    overe
    -0.54
    çīĪ
    -0.53
    RAL
    -0.53
    POSITIVE LOGITS
     appearances
    0.96
     pace
    0.80
     footing
    0.70
    ency
    0.69
    endra
    0.69
    standing
    0.67
    ouver
    0.66
     momentum
    0.65
     persistence
    0.65
    rate
    0.65
    Activations Density 0.032%

    No Known Activations