© 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. 9-RES-JB
    11. 11242
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "take up" used in various contexts

    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
    lua
    -0.78
    ¯
    -0.78
    gets
    -0.74
    geist
    -0.70
    come
    -0.68
    jah
    -0.67
    bey
    -0.67
    WARNING
    -0.67
    jong
    -0.65
    tu
    -0.65
    POSITIVE LOGITS
     residence
    1.23
     arms
    0.86
     slack
    0.78
     positions
    0.77
    rights
    0.77
     position
    0.77
     residency
    0.75
     sugg
    0.69
    ibilities
    0.69
     hobbies
    0.67
    Activations Density 0.031%

    No Known Activations