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. 3-RES-JB
    6. 8417
    Prev
    Next
    INDEX
    Explanations

    positive adjectives related to hospitality and friendliness

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hospitality and a welcoming atmosphere

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibur
    -0.75
    chem
    -0.73
    orah
    -0.71
    acea
    -0.69
    ulz
    -0.69
    oggles
    -0.67
    rag
    -0.67
    ibrary
    -0.66
    Ultra
    -0.66
    iane
    -0.65
    POSITIVE LOGITS
     welcoming
    0.97
    glers
    0.83
     welcome
    0.82
     welcomes
    0.76
     guests
    0.75
     venues
    0.70
     climates
    0.70
     hosts
    0.68
    ctuary
    0.67
     ambassadors
    0.67
    Activations Density 0.019%

    No Known Activations