© 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. 4-RES-JB
    11. 15338
    Prev
    Next
    INDEX
    Explanations

    terms related to technical and scientific subjects, particularly acronyms and specialized vocabulary

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and environmental themes

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

    No Comments

    Negative Logits
    lain
    -0.74
    laus
    -0.72
    /_
    -0.64
     ..........
    -0.61
    rss
    -0.60
    âķIJâķIJ
    -0.57
    beat
    -0.57
    erella
    -0.57
     Gutierrez
    -0.56
    abba
    -0.55
    POSITIVE LOGITS
    ailability
    0.62
     citiz
    0.61
    caster
    0.61
    acco
    0.60
     rul
    0.60
     workforce
    0.59
     monop
    0.58
    existence
    0.58
     movements
    0.57
    fighter
    0.57
    Activations Density 0.941%

    No Known Activations