© 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. 8-RES-JB
    11. 19406
    Prev
    Next
    INDEX
    Explanations

    references to scrap materials or objects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discarded or leftover materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    secut
    -0.72
     simultane
    -0.69
    CVE
    -0.68
    quickShipAvailable
    -0.67
     uncond
    -0.66
     conspicuous
    -0.64
     relativity
    -0.62
     attentive
    -0.62
     Prol
    -0.62
     unconditional
    -0.60
    POSITIVE LOGITS
    yard
    1.07
    shaw
    0.98
    yards
    0.92
    book
    0.89
    books
    0.88
    aper
    0.87
    enhagen
    0.83
    hire
    0.83
    ible
    0.81
    bones
    0.80
    Activations Density 0.029%

    No Known Activations