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. 9-RES-JB
    6. 8425
    Prev
    Next
    INDEX
    Explanations

    words expressing a preference or a choice

    oai_token-act-pair · gpt-3.5-turbo

    the usage of the word "prefer" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brance
    -1.04
    STATE
    -0.70
    arta
    -0.69
    ãĥĥãĤ¯
    -0.68
    gren
    -0.68
    meta
    -0.67
    breakers
    -0.66
    DragonMagazine
    -0.66
    orig
    -0.66
    Impl
    -0.66
    POSITIVE LOGITS
    rals
    0.91
    ably
    0.75
     anonymity
    0.74
     solitude
    0.73
    itism
    0.70
     staying
    0.70
     embodiments
    0.69
     endings
    0.69
     preferring
    0.66
     monog
    0.65
    Activations Density 0.039%

    No Known Activations