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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 78
    Prev
    Next
    INDEX
    Explanations

    words related to a specific place or name, specifically "Marg"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Margaret" or its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fulness
    -0.85
    pmwiki
    -0.79
    enegger
    -0.78
    ctor
    -0.76
     hearing
    -0.70
    ÄŁ
    -0.70
    spe
    -0.70
    FUL
    -0.70
    INESS
    -0.69
    ãģ¦
    -0.68
    POSITIVE LOGITS
    aret
    1.18
    olis
    1.06
    inal
    0.97
    reet
    0.94
    inally
    0.88
    acies
    0.87
    olicy
    0.86
    iana
    0.86
    arine
    0.83
    inals
    0.83
    Activations Density 0.013%

    No Known Activations