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. 15381
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of 'dip'

    oai_token-act-pair · gpt-3.5-turbo

    references to decreases or declines

    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
     ACTIONS
    -0.75
    Made
    -0.74
    fare
    -0.72
    Reply
    -0.72
     Crusade
    -0.72
    ÙIJ
    -0.68
     Machina
    -0.63
    apes
    -0.63
    furt
    -0.62
     Gemini
    -0.62
    POSITIVE LOGITS
    shit
    1.20
    pty
    1.02
     dipping
    0.99
    otom
    0.95
    artisan
    0.94
    idon
    0.92
    tera
    0.91
    irts
    0.91
    ole
    0.87
    iphany
    0.87
    Activations Density 0.026%

    No Known Activations