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. 3216
    Prev
    Next
    INDEX
    Explanations

    proper names, likely related to technology or gaming

    oai_token-act-pair · gpt-3.5-turbo

    mentions of people or notable figures

    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
    .")
    -0.77
    ]."
    -0.71
     attRot
    -0.69
    .).
    -0.68
    sic
    -0.68
    )).
    -0.67
    cms
    -0.66
    '."
    -0.66
    >.
    -0.65
    $.
    -0.62
    POSITIVE LOGITS
     FG
    0.59
     Avalon
    0.57
     renamed
    0.54
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.54
    ometown
    0.53
     Located
    0.53
     Originally
    0.52
     hybrids
    0.52
     Buenos
    0.51
    amia
    0.50
    Activations Density 1.153%

    No Known Activations