© 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. 2-RES-JB
    11. 19605
    Prev
    Next
    INDEX
    Explanations

    verbs related to reduction or decrease

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "shrink."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̶
    -0.68
     QC
    -0.67
    ixture
    -0.66
    rera
    -0.66
    role
    -0.63
    cause
    -0.62
     Judicial
    -0.62
    alez
    -0.62
     Bloody
    -0.60
     Universal
    -0.60
    POSITIVE LOGITS
     shrink
    1.12
     shrunk
    0.96
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.93
     shrinking
    0.92
    abies
    0.86
    shr
    0.84
     violet
    0.81
    aroo
    0.76
    eness
    0.73
    flation
    0.73
    Activations Density 0.008%

    No Known Activations