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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 14245
    Prev
    Next
    INDEX
    Explanations

    names or titles indicating leadership positions in various organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals holding the title of "president."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    γ
    -0.59
    Dark
    -0.58
     darkness
    -0.58
    tro
    -0.58
     Peaks
    -0.57
     Nightmares
    -0.57
    Medium
    -0.56
     ease
    -0.56
    INGTON
    -0.55
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.55
    POSITIVE LOGITS
    ially
    1.23
    ial
    1.05
    clinton
    0.99
     emer
    0.95
    iors
    0.92
    boards
    0.88
    aroo
    0.85
    IAL
    0.85
    dom
    0.81
    eki
    0.75
    Activations Density 0.053%

    No Known Activations