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. 0-RES-JB
    6. 3577
    Prev
    Next
    INDEX
    Explanations

    advice or recommendations being given to individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "advise."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attm
    -0.66
    historic
    -0.66
    âĿ
    -0.65
    fest
    -0.62
     Takeru
    -0.61
     BUR
    -0.61
    iny
    -0.60
     Tears
    -0.57
     shred
    -0.57
    kai
    -0.57
    POSITIVE LOGITS
     advise
    3.46
     advising
    3.25
     advises
    3.00
     advised
    2.32
     advice
    1.91
     Advice
    1.65
     recommending
    1.64
     recommends
    1.63
     advisory
    1.61
     recommend
    1.56
    Activations Density 0.025%

    No Known Activations