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. 3-RES-JB
    6. 10203
    Prev
    Next
    INDEX
    Explanations

    terms related to semiconductor technology

    oai_token-act-pair · gpt-3.5-turbo

    references to semiconductor technology and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.93
    hood
    -0.72
    DragonMagazine
    -0.71
    tenance
    -0.70
     Maid
    -0.69
    WARE
    -0.67
    theless
    -0.67
    STD
    -0.67
    EngineDebug
    -0.66
    BF
    -0.65
    POSITIVE LOGITS
    aped
    1.09
    onduct
    1.06
    apers
    1.05
    aps
    1.02
    aping
    0.98
    rop
    0.97
    apped
    0.94
    appers
    0.94
    opic
    0.93
    itating
    0.92
    Activations Density 0.019%

    No Known Activations