© 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. 10-RES-JB
    11. 18827
    Prev
    Next
    INDEX
    Explanations

    words related to actions or strategies in handling various situations

    oai_token-act-pair · gpt-3.5-turbo

    words associated with systems and processes in various contexts

    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
    Enlarge
    -0.65
     clin
    -0.63
     suppose
    -0.60
     Looking
    -0.60
     viz
    -0.59
    \'
    -0.56
     headlined
    -0.56
     rocked
    -0.55
     anchored
    -0.55
    sectional
    -0.54
    POSITIVE LOGITS
    lessly
    1.23
    ulate
    1.13
    ify
    1.11
    orously
    0.97
    uate
    0.93
    ize
    0.92
    imize
    0.92
    ise
    0.90
    matically
    0.88
    ishly
    0.87
    Activations Density 0.394%

    No Known Activations