© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3028
    Prev
    Next
    INDEX
    Explanations

    explicit conditions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    criteria and requirements related to formal evaluations or assessments

    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
    awaru
    -0.68
     forever
    -0.67
    href
    -0.66
     anymore
    -0.66
    ocaust
    -0.65
     impunity
    -0.64
    laugh
    -0.63
    ouble
    -0.62
    ratom
    -0.62
     somebody
    -0.61
    POSITIVE LOGITS
     requirements
    1.42
     precautions
    1.27
     parameters
    1.26
     hurdles
    1.23
     aspects
    1.22
     steps
    1.19
    requisites
    1.19
     details
    1.18
     qualifications
    1.18
     prerequisite
    1.16
    Activations Density 0.618%

    No Known Activations