© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8125
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms and concepts, possibly related to research or academia

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific analysis and representation

    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
     TRAN
    -0.53
    ãĥ©ãĥ³
    -0.53
    egu
    -0.52
     Temporary
    -0.51
     denotes
    -0.50
    estern
    -0.49
    announced
    -0.49
    imon
    -0.48
     whistle
    -0.48
    ModLoader
    -0.47
    POSITIVE LOGITS
     anymore
    1.25
     anyways
    0.98
    >.
    0.98
     anyway
    0.96
     whatsoever
    0.96
    .</
    0.95
    _.
    0.95
    ]).
    0.93
     nor
    0.92
    .).
    0.88
    Activations Density 1.042%

    No Known Activations