© 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. 1492
    Prev
    Next
    INDEX
    Explanations

    scientific or investigative terms related to analyzing and identifying specific patterns or entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to identification and tracking of entities or behaviors

    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
    ©¶æ¥µ
    -0.81
    --------------------------------------------------------
    -0.71
    addin
    -0.70
    ħĭ
    -0.68
    DES
    -0.68
    amon
    -0.64
    ruary
    -0.61
     Extended
    -0.61
    ustomed
    -0.59
    wark
    -0.59
    POSITIVE LOGITS
     contaminants
    0.91
     offenders
    0.83
     suspicious
    0.81
     entries
    0.81
     stray
    0.81
     excess
    0.78
     traces
    0.77
    bugs
    0.77
     contamin
    0.77
     missing
    0.77
    Activations Density 0.897%

    No Known Activations