© 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. 11-RES-JB
    11. 11800
    Prev
    Next
    INDEX
    Explanations

    phrases related to sequence or order of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate sequential actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Played
    -0.76
    Especially
    -0.74
    JV
    -0.71
     Killed
    -0.68
     Tradable
    -0.66
     Created
    -0.63
    ahime
    -0.63
     Subscribe
    -0.62
     Especially
    -0.61
    zsche
    -0.60
    POSITIVE LOGITS
    ward
    1.65
    wards
    1.57
    math
    1.13
    noon
    1.07
     exchanging
    1.02
    words
    1.02
     awhile
    0.99
     consulting
    0.91
     inspecting
    0.89
     completing
    0.89
    Activations Density 0.121%

    No Known Activations