© 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. 4-RES-JB
    11. 14317
    Prev
    Next
    INDEX
    Explanations

    technical content related to coding or formatting, particularly focused on special characters and syntax

    oai_token-act-pair · gpt-3.5-turbo

    references to digital content organization or structuring

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

    No Comments

    Negative Logits
    ndum
    -0.88
    cephal
    -0.74
    lihood
    -0.71
    Weak
    -0.69
    mens
    -0.69
    psey
    -0.67
    yip
    -0.66
    apego
    -0.66
    Pred
    -0.65
    lehem
    -0.65
    POSITIVE LOGITS
    aez
    0.69
    displayText
    0.67
    Ĥİ
    0.62
    isSpecialOrderable
    0.61
     mortgage
    0.60
     tuition
    0.59
    é¾į
    0.59
    interstitial
    0.57
    Duration
    0.57
    heny
    0.56
    Activations Density 0.060%

    No Known Activations