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. 11308
    Prev
    Next
    INDEX
    Explanations

    mentions of electronic books

    oai_token-act-pair · gpt-3.5-turbo

    references to electronic communication systems, particularly emails

    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
    ãĤ¤ãĥĪ
    -0.81
     Kitchen
    -0.79
     Katz
    -0.75
     Anthem
    -0.71
     Kats
    -0.71
     Revel
    -0.66
     Painter
    -0.66
    å§«
    -0.64
    DOWN
    -0.64
    éĹĺ
    -0.63
    POSITIVE LOGITS
    tymology
    1.32
    gypt
    1.17
    ugen
    1.17
    ighth
    1.16
    agles
    1.15
    arthed
    1.15
    ternally
    1.14
    igen
    1.04
    thereum
    1.01
    ucl
    1.00
    Activations Density 0.020%

    No Known Activations