© 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. 9-RES-JB
    11. 3364
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming and text processing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to language classification and grammatical structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MpServer
    -0.83
    MRI
    -0.82
    artifacts
    -0.72
    uala
    -0.72
    atcher
    -0.69
    romeda
    -0.66
    ARC
    -0.64
    planned
    -0.64
    keye
    -0.63
    Scene
    -0.63
    POSITIVE LOGITS
     noun
    1.84
     adject
    1.74
     phrases
    1.71
     verbs
    1.70
     adjective
    1.66
     suffix
    1.65
     phrase
    1.64
     words
    1.62
     pronouns
    1.53
     verb
    1.51
    Activations Density 1.425%

    No Known Activations