Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15933
    Prev
    Next
    INDEX
    Explanations

    keywords related to SD cards and storage devices

    oai_token-act-pair · gpt-3.5-turbo

    references to SD (secure digital) cards or storage formats

    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
     comb
    -0.87
    emis
    -0.79
     bot
    -0.72
    vier
    -0.71
     Wonderland
    -0.68
    jing
    -0.67
    ocrates
    -0.65
     Berger
    -0.64
     Haitian
    -0.63
     rejo
    -0.63
    POSITIVE LOGITS
     SD
    4.02
    SD
    2.66
     sd
    2.19
    sd
    1.71
     SDL
    1.39
     SF
    1.29
     WD
    1.29
     ND
    1.26
     UD
    1.24
     DF
    1.24
    Activations Density 0.011%

    No Known Activations