© 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. 4679
    Prev
    Next
    INDEX
    Explanations

    actions that involve physical movement and locations

    oai_token-act-pair · gpt-3.5-turbo

    actions and processes related to control and management

    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
     Nationals
    -0.55
    elong
    -0.52
    gor
    -0.51
     ts
    -0.50
     Hung
    -0.49
    inen
    -0.47
    ahon
    -0.47
    ikk
    -0.46
    ©¶æ
    -0.46
    yip
    -0.46
    POSITIVE LOGITS
     accordingly
    1.56
     thereafter
    1.32
     afterward
    1.14
     afterwards
    1.13
    .
    0.96
    .[
    0.96
    .<
    0.94
     therein
    0.93
    .(
    0.89
     thereof
    0.87
    Activations Density 1.254%

    No Known Activations