© 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. 8-RES-JB
    11. 4605
    Prev
    Next
    INDEX
    Explanations

    terms related to the web and internet technology

    oai_token-act-pair · gpt-3.5-turbo

    references to web-related technologies and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marketable
    -0.77
    trump
    -0.76
    tein
    -0.75
    nen
    -0.71
    Lago
    -0.71
    tre
    -0.65
     [|
    -0.64
     tremend
    -0.64
    seq
    -0.63
     Triangle
    -0.63
    POSITIVE LOGITS
     browsers
    0.80
     Torrent
    0.74
    browser
    0.73
    phrine
    0.73
     providers
    0.72
    ologies
    0.71
     Apps
    0.70
    archive
    0.70
    annels
    0.70
    accessible
    0.70
    Activations Density 0.247%

    No Known Activations