Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 9234
    Prev
    Next
    INDEX
    Explanations

    verbs or nouns denoting significant or impactful actions or concepts

    oai_token-act-pair · gpt-3.5-turbo

    musical or thematic elements and structures within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BSD
    -0.73
    phia
    -0.72
    Charge
    -0.70
     Masters
    -0.69
    ADS
    -0.69
    bilt
    -0.65
     attraction
    -0.65
    pire
    -0.65
     ADA
    -0.65
    dash
    -0.64
    POSITIVE LOGITS
    oring
    1.05
    ored
    1.00
    arding
    0.96
    oured
    0.93
    ouring
    0.88
    roup
    0.86
    uilding
    0.84
    orer
    0.83
    orers
    0.82
    oning
    0.81
    Activations Density 0.026%

    No Known Activations