© 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. 17680
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe intensity or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptive words and terms related to film and societal themes

    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
    OIL
    -0.84
    uther
    -0.81
    avia
    -0.79
    qqa
    -0.79
    redits
    -0.78
     besides
    -0.76
    chwitz
    -0.76
    Specific
    -0.75
    registered
    -0.75
    RF
    -0.75
    POSITIVE LOGITS
     nature
    1.14
     confines
    1.06
     USS
    1.02
     portion
    1.00
     aspect
    0.93
     masses
    0.91
     version
    0.89
     process
    0.89
     portions
    0.88
     world
    0.87
    Activations Density 0.332%

    No Known Activations