Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12006
    Prev
    Next
    INDEX
    Explanations

    words related to electronics and soldering

    oai_token-act-pair · gpt-3.5-turbo

    components and processes related to electronics and circuit assembly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.71
    itia
    -0.68
    ebin
    -0.68
     Winner
    -0.68
     Ridley
    -0.67
    Winner
    -0.66
     Cruise
    -0.65
    Brave
    -0.65
     judgment
    -0.64
    Ban
    -0.64
    POSITIVE LOGITS
     piping
    0.98
     wiring
    0.96
    uctor
    0.95
     wires
    0.92
     cables
    0.91
     circuitry
    0.91
     voltage
    0.87
     harness
    0.86
     wire
    0.86
     filament
    0.84
    Activations Density 0.074%

    No Known Activations