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. 2-RES-JB
    6. 9582
    Prev
    Next
    INDEX
    Explanations

    advice or recommendations given by someone to others

    oai_token-act-pair · gpt-3.5-turbo

    words related to giving advice or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á
    -0.81
    ppa
    -0.73
    BU
    -0.69
    Î
    -0.69
    anuts
    -0.68
     McA
    -0.66
    mb
    -0.66
    imb
    -0.65
    morph
    -0.65
    Bon
    -0.65
    POSITIVE LOGITS
     advising
    1.29
     advised
    1.19
     advise
    1.10
     advises
    1.07
     advice
    0.89
     caution
    0.87
     counsel
    0.84
     Advice
    0.83
    recomm
    0.79
     recommended
    0.78
    Activations Density 0.010%

    No Known Activations