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. 1662
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific entity named "Parent"

    oai_token-act-pair · gpt-3.5-turbo

    mentions and discussions related to parental roles and controls

    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
    hiba
    -0.88
    ×ķ
    -0.74
    ×Ķ
    -0.72
    NRS
    -0.67
    cephal
    -0.67
     doub
    -0.64
     discounted
    -0.64
    ×IJ
    -0.63
    cigarettes
    -0.62
    BILITY
    -0.62
    POSITIVE LOGITS
    edIn
    0.99
    alys
    0.92
    ordial
    0.91
    į
    0.91
    names
    0.90
    icipated
    0.89
    icides
    0.89
    rikes
    0.89
    ing
    0.87
    ality
    0.87
    Activations Density 0.010%

    No Known Activations