© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10416
    Prev
    Next
    INDEX
    Explanations

    terms related to giving or receiving advice

    oai_token-act-pair · gpt-3.5-turbo

    references to advice

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

    No Comments

    Negative Logits
    bang
    -0.67
    oor
    -0.63
     Alive
    -0.63
    lock
    -0.62
     Classics
    -0.62
     Democr
    -0.61
     psy
    -0.61
    lat
    -0.59
    dimension
    -0.59
     Seas
    -0.58
    POSITIVE LOGITS
     Advice
    1.08
     advice
    1.08
     advise
    0.89
     advising
    0.88
     recommendation
    0.82
     advised
    0.81
    urai
    0.79
    arial
    0.79
     recommendations
    0.78
     paralysis
    0.77
    Activations Density 0.016%

    No Known Activations