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. 7-RES-JB
    6. 10447
    Prev
    Next
    INDEX
    Explanations

    computer code snippets and configuration settings

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to web administration and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    packing
    -0.69
    DEM
    -0.61
    stad
    -0.60
    aiman
    -0.60
     Sixth
    -0.60
     simul
    -0.58
    pas
    -0.58
     boarding
    -0.58
     guerrilla
    -0.58
    uchin
    -0.58
    POSITIVE LOGITS
    acters
    0.83
    ÙĴ
    0.80
    estic
    0.80
     }}
    0.75
    )=(
    0.74
    \
    0.74
    alog
    0.73
    Ùİ
    0.72
    anooga
    0.72
    е
    0.70
    Activations Density 0.038%

    No Known Activations