© 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. 4-RES-JB
    6. 9307
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to activation processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to activation processes and triggers

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

    No Comments

    Negative Logits
    esan
    -0.77
     Abram
    -0.68
    apest
    -0.67
    umbo
    -0.67
     Hague
    -0.64
    elf
    -0.64
    ago
    -0.62
     Tale
    -0.62
     Apost
    -0.62
     Norman
    -0.62
    POSITIVE LOGITS
     activation
    1.01
     activated
    0.89
     charcoal
    0.84
     activate
    0.84
    activation
    0.83
    activated
    0.82
     activating
    0.81
     activates
    0.81
     activ
    0.80
    uates
    0.74
    Activations Density 0.015%

    No Known Activations