© 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. 8-RES-JB
    11. 4622
    Prev
    Next
    INDEX
    Explanations

    mentions of new regulations, laws, or rules

    oai_token-act-pair · gpt-3.5-turbo

    references to recent legislation or new laws

    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
    umenthal
    -0.81
    ecause
    -0.77
    oleon
    -0.77
    ashtra
    -0.77
    ertodd
    -0.77
    acebook
    -0.77
    Zip
    -0.75
    lua
    -0.75
    cius
    -0.73
     teasp
    -0.73
    POSITIVE LOGITS
    bies
    1.37
    bie
    1.35
     arrivals
    1.15
     millennium
    1.15
     edition
    0.98
     generation
    0.96
     era
    0.93
     additions
    0.92
     incarnation
    0.90
     paradigm
    0.89
    Activations Density 0.084%

    No Known Activations