© 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. 8-RES-JB
    11. 8325
    Prev
    Next
    INDEX
    Explanations

    words related to automatic or automated systems

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "automatic" in various contexts

    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
    ĸļ
    -1.00
    borough
    -0.90
    代
    -0.87
    apest
    -0.86
    rug
    -0.82
    arte
    -0.81
    gdala
    -0.80
    ours
    -0.78
    akov
    -0.77
    ORK
    -0.75
    POSITIVE LOGITS
     transmission
    1.27
     transmissions
    0.97
     braking
    0.96
    ity
    0.95
    ized
    0.90
     renewal
    0.84
     conversion
    0.83
    izable
    0.83
    omatic
    0.82
     termination
    0.81
    Activations Density 0.029%

    No Known Activations