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. 0-RES-JB
    6. 23024
    Prev
    Next
    INDEX
    Explanations

    ACronyms related to government departments or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of regulatory commissions or agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -0.69
     mug
    -0.69
     Pearl
    -0.67
     warm
    -0.66
     sake
    -0.66
     ink
    -0.65
     waiter
    -0.63
     illusion
    -0.62
     Fare
    -0.62
    */(
    -0.62
    POSITIVE LOGITS
    RC
    4.39
    rc
    2.01
     RC
    1.78
    RS
    1.64
    RL
    1.48
    CCC
    1.47
    ERC
    1.43
    RP
    1.42
    VC
    1.39
     CRC
    1.35
    Activations Density 0.014%

    No Known Activations