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. 9-RES-JB
    6. 10941
    Prev
    Next
    INDEX
    Explanations

    technical terms related to physical forces and properties like electric field, pressure variation, and gravitational field

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to physics and engineering processes

    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
    ploma
    -0.73
    kie
    -0.70
    aghd
    -0.70
     Homeless
    -0.68
    uscript
    -0.68
     Dek
    -0.67
     Campus
    -0.67
    folk
    -0.67
    adult
    -0.65
    udget
    -0.65
    POSITIVE LOGITS
     coefficient
    1.31
     gradient
    1.25
     coefficients
    1.19
     amplitude
    1.11
     velocity
    1.09
     propagation
    1.08
     exerted
    1.06
     currents
    1.03
     damp
    1.01
     modulation
    1.01
    Activations Density 0.307%

    No Known Activations