© 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. 19369
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions of putting or physically arranging objects

    oai_token-act-pair · gpt-3.5-turbo

    references to actions involving placing or positioning entities

    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
    etheless
    -0.62
    ority
    -0.60
    days
    -0.60
     Heist
    -0.59
     sqor
    -0.57
    arious
    -0.56
    bidden
    -0.56
    ALSE
    -0.56
    oris
    -0.55
    Container
    -0.55
    POSITIVE LOGITS
     aside
    0.94
     squarely
    0.89
     together
    0.82
     into
    0.80
     smack
    0.77
     firmly
    0.77
     toget
    0.76
     "$:/
    0.75
     finishing
    0.73
     onto
    0.71
    Activations Density 0.154%

    No Known Activations