© 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. 6-RES-JB
    11. 18437
    Prev
    Next
    INDEX
    Explanations

    dates expressed in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.75
    etheless
    -0.73
    Reloaded
    -0.65
    isode
    -0.64
    ascular
    -0.64
    reditary
    -0.63
    rontal
    -0.62
    itri
    -0.59
     Gleaming
    -0.59
    Topics
    -0.58
    POSITIVE LOGITS
    lang
    0.72
     Quan
    0.71
    ħĭ
    0.68
    fi
    0.64
     reader
    0.63
    si
    0.63
    é¾
    0.62
    ciating
    0.60
     tremend
    0.59
     Lauder
    0.58
    Activations Density 0.790%

    No Known Activations