© 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 EvalsExportsinterp-engineNEWAPI 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. 24342
    Prev
    Next
    INDEX
    Explanations

    descriptions of objects created from raw materials

    oai_token-act-pair · gpt-3.5-turbo

    references to food or ingredients and their sources

    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
    "]=>
    -0.73
    ardless
    -0.73
    stop
    -0.69
    atform
    -0.67
    oming
    -0.67
    ovation
    -0.62
    orescence
    -0.62
    osion
    -0.61
     succeeds
    -0.60
    uber
    -0.60
    POSITIVE LOGITS
     previously
    0.83
     pree
    0.77
     notor
    0.75
     traditionally
    0.75
     customary
    0.74
     previous
    0.73
     existing
    0.72
     predecessors
    0.72
     ancestors
    0.71
     childhood
    0.69
    Activations Density 0.804%

    No Known Activations