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. 4-RES-JB
    6. 5121
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Junior"

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "ior" which indicates a linguistic or thematic focus on comparative qualities or specialties

    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
    lished
    -0.90
    soDeliveryDate
    -0.82
    ivity
    -0.80
    isSpecialOrderable
    -0.75
    alogue
    -0.71
    ENDED
    -0.68
    sheet
    -0.67
    utch
    -0.65
    sembly
    -0.63
    è¦ļéĨĴ
    -0.63
    POSITIVE LOGITS
    gio
    1.25
    ior
    1.13
    ama
    0.87
    IOR
    0.85
    iculture
    0.85
    acies
    0.82
    tarian
    0.80
    ity
    0.80
     dilig
    0.76
    acy
    0.75
    Activations Density 0.011%

    No Known Activations