© 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. 2-RES-JB
    11. 14010
    Prev
    Next
    INDEX
    Explanations

    words related to architecture

    oai_token-act-pair · gpt-3.5-turbo

    terms related to architecture and architects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lling
    -0.77
     Canaver
    -0.75
    lli
    -0.74
    cussion
    -0.72
    thening
    -0.71
    ndra
    -0.70
    berman
    -0.70
    tto
    -0.68
    udge
    -0.66
     Cancel
    -0.65
    POSITIVE LOGITS
    itect
    1.60
    arch
    1.18
    ipel
    1.04
    arist
    0.93
    ief
    0.90
    archy
    0.86
    ival
    0.86
    osaurs
    0.86
    ivist
    0.82
    opoulos
    0.81
    Activations Density 0.007%

    No Known Activations