Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 12461
    Prev
    Next
    INDEX
    Explanations

    preferences or popular choices

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "favorite" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urers
    -0.79
    inas
    -0.77
    ural
    -0.76
    idental
    -0.75
    OUT
    -0.74
    heed
    -0.74
    abeth
    -0.74
    okin
    -0.72
    absor
    -0.71
    roup
    -0.71
    POSITIVE LOGITS
     favorites
    0.92
     haunt
    0.89
     favorite
    0.84
     darling
    0.83
     underdog
    0.76
     haun
    0.74
     amongst
    0.73
    é¾įå¥ij士
    0.70
    é¾įå
    0.70
     whipping
    0.69
    Activations Density 0.016%

    No Known Activations