© 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. 10-RES-JB
    11. 13576
    Prev
    Next
    INDEX
    Explanations

    messy or chaotic situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    actions or conditions related to struggles or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complying
    -0.72
     dealing
    -0.70
     informing
    -0.68
     distinguishing
    -0.68
     serving
    -0.68
     attribution
    -0.67
     obtaining
    -0.65
     providing
    -0.65
     detecting
    -0.65
     suffering
    -0.64
    POSITIVE LOGITS
    wrote
    1.37
    ked
    1.33
    rolled
    1.32
    igrated
    1.32
    overed
    1.29
    ayed
    1.26
    ounced
    1.23
    eared
    1.22
    pered
    1.21
    iked
    1.21
    Activations Density 0.257%

    No Known Activations