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. 6-RES-JB
    6. 1189
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of support or endorsements

    oai_token-act-pair · gpt-3.5-turbo

    the word "supp" and its variations, indicating a focus on support-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.75
     Admir
    -0.73
     Nanto
    -0.69
     logger
    -0.68
    âĹ¼
    -0.68
     Babel
    -0.67
    EStream
    -0.66
     Abyssal
    -0.65
     Wilde
    -0.65
     Warsaw
    -0.64
    POSITIVE LOGITS
    lication
    1.27
    orter
    1.17
    ressive
    1.16
    lied
    1.13
    osition
    1.12
    ression
    1.10
    ressed
    1.10
    orters
    1.07
    ortun
    1.06
    ressing
    1.05
    Activations Density 0.013%

    No Known Activations