© 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. 10-RES-JB
    11. 20435
    Prev
    Next
    INDEX
    Explanations

    technical terms related to equipment and installation in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of compatibility and fitting of electronic components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.89
    eming
    -0.80
    Percent
    -0.76
    ;;;;;;;;;;;;
    -0.75
    perse
    -0.73
    wat
    -0.71
    Rank
    -0.70
    onyms
    -0.69
    parency
    -0.67
    arcity
    -0.67
    POSITIVE LOGITS
     chassis
    1.34
     underside
    1.09
     cabinets
    1.08
     forearm
    1.07
     motherboard
    1.07
     backpack
    1.06
     enclosure
    1.06
     tripod
    1.02
     cabinet
    1.02
     rack
    1.02
    Activations Density 0.276%

    No Known Activations