© 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. 8391
    Prev
    Next
    INDEX
    Explanations

    words related to technology, specifically focusing on ROM (Read-Only Memory)

    oai_token-act-pair · gpt-3.5-turbo

    references to technical specifications related to software or hardware

    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
     Louise
    -0.81
    atche
    -0.80
    Jamie
    -0.80
     Dra
    -0.78
     Dover
    -0.77
     Edinburgh
    -0.76
     Gö
    -0.76
     Highlands
    -0.75
     Wool
    -0.74
    hof
    -0.74
    POSITIVE LOGITS
     ROM
    2.47
     rooting
    1.99
     rooted
    1.93
    ROM
    1.83
     Cyan
    1.70
     firmware
    1.44
     OnePlus
    1.44
     CM
    1.43
     rom
    1.38
    OSP
    1.35
    Activations Density 0.041%

    No Known Activations