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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4264
    Prev
    Next
    INDEX
    Explanations

    various phrases that start with "putting it" or "saying it" in different ways

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express ways to simplify or clarify complex ideas

    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
    ãĥĻ
    -0.72
    aceous
    -0.71
    irlf
    -0.70
    ettings
    -0.67
    ourses
    -0.67
    OUND
    -0.66
    emis
    -0.66
    ģ«
    -0.64
    Course
    -0.64
    borg
    -0.64
    POSITIVE LOGITS
     hypot
    0.67
    quote
    0.65
     Kev
    0.64
     bluntly
    0.62
     caps
    0.62
    Merit
    0.59
     amen
    0.58
     Pf
    0.57
    caps
    0.56
    loc
    0.55
    Activations Density 0.261%

    No Known Activations