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. 2-RES-JB
    6. 5093
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person, "Aguilera"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those with the name "Agu."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.90
    Doctors
    -0.66
    FACE
    -0.66
     photoc
    -0.64
    Leaks
    -0.64
     Ré
    -0.63
    Micro
    -0.63
    士
    -0.63
     Scouting
    -0.63
    WARE
    -0.63
    POSITIVE LOGITS
    inis
    0.98
    ahah
    0.93
    selage
    0.93
    anas
    0.85
    ilar
    0.84
    imag
    0.83
    alach
    0.83
    inia
    0.82
    awatts
    0.81
    racuse
    0.80
    Activations Density 0.013%

    No Known Activations