© 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. 12599
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the end or resolution of a situation or issue

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant contributions or impacts 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
     Digest
    -0.67
     Learns
    -0.60
     Supported
    -0.58
     Received
    -0.57
     Unle
    -0.56
    arious
    -0.56
     Cavern
    -0.56
     Incarn
    -0.56
    ÃĥÃĤ
    -0.55
    edom
    -0.54
    POSITIVE LOGITS
     emphasis
    1.11
     brakes
    1.08
     spotlight
    0.96
     moratorium
    0.91
     lid
    0.89
     dent
    0.88
     limits
    0.84
     burden
    0.84
     restraints
    0.84
     stamp
    0.84
    Activations Density 0.078%

    No Known Activations