© 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. 0-RES-JB
    11. 5346
    Prev
    Next
    INDEX
    Explanations

    terms related to neural activity and networks

    oai_token-act-pair · gpt-3.5-turbo

    references to neural networks and associated terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tar
    -0.84
    iqu
    -0.80
    zone
    -0.80
    owner
    -0.73
    bish
    -0.73
     Sho
    -0.69
     Tit
    -0.69
     Vend
    -0.67
    âĢİ
    -0.67
    west
    -0.66
    POSITIVE LOGITS
     neural
    3.49
     Neural
    2.92
     neuronal
    1.94
     neuro
    1.75
     neurons
    1.73
     neuron
    1.72
     cortical
    1.69
     neur
    1.68
     neurological
    1.65
     synaptic
    1.56
    Activations Density 0.029%

    No Known Activations