© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 19793
    Prev
    Next
    INDEX
    Explanations

    references to physical objects like bolts, wires, cables, and connectors

    oai_token-act-pair · gpt-3.5-turbo

    references to electrical or mechanical components and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.81
     Nights
    -0.77
    sych
    -0.76
    ioch
    -0.74
    ternity
    -0.74
    eatures
    -0.71
    PDATE
    -0.68
    Day
    -0.67
    rians
    -0.67
    eanor
    -0.65
    POSITIVE LOGITS
     protr
    1.04
     rods
    1.00
     mesh
    0.99
     severed
    0.97
     dangling
    0.95
     rod
    0.94
     diameter
    0.93
     connecting
    0.89
     rope
    0.88
     attached
    0.87
    Activations Density 0.093%

    No Known Activations