© 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 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. 3-RES-JB
    11. 5557
    Prev
    Next
    INDEX
    Explanations

    terms related to actions or processes being initiated or put into effect

    oai_token-act-pair · gpt-3.5-turbo

    terms related to activation processes or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esan
    -0.73
    elf
    -0.69
    aco
    -0.66
     Hague
    -0.66
    apest
    -0.66
     Abram
    -0.65
     Tale
    -0.65
    opic
    -0.64
    umbo
    -0.63
     Ange
    -0.61
    POSITIVE LOGITS
     activation
    1.01
     activated
    0.93
    activation
    0.88
    uates
    0.84
    activated
    0.83
     charcoal
    0.83
     activates
    0.82
     activ
    0.82
     activating
    0.80
     activate
    0.80
    Activations Density 0.011%

    No Known Activations