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. 601
    Prev
    Next
    INDEX
    Explanations

    attributes related to products such as being inexpensive, lasting, versatile, creamy, light, and resistant

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to value and quality

    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
    rued
    -0.80
    IED
    -0.74
    regate
    -0.72
    OHN
    -0.72
     Anger
    -0.72
    onica
    -0.71
    endar
    -0.71
    pta
    -0.70
    moil
    -0.70
    udence
    -0.69
    POSITIVE LOGITS
     contains
    1.11
     emits
    1.05
     inexpensive
    1.03
     fits
    1.00
     weighs
    0.99
     reusable
    0.98
     versatile
    0.98
     easy
    0.97
     priced
    0.97
     boasts
    0.97
    Activations Density 0.299%

    No Known Activations