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. 18447
    Prev
    Next
    INDEX
    Explanations

    phrases related to fictional worlds or franchises

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the definite article "the."

    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
    etheless
    -0.70
    fulness
    -0.69
     vandalism
    -0.68
     fate
    -0.68
     conservatism
    -0.68
     policy
    -0.67
     liking
    -0.67
     alas
    -0.67
     tolerance
    -0.67
     contention
    -0.67
    POSITIVE LOGITS
     Ancients
    1.04
     Dead
    1.03
     Elements
    1.00
     Bottle
    0.99
     Serpent
    0.99
     Past
    0.97
     Void
    0.96
     Knife
    0.96
     Owl
    0.93
     Unknown
    0.93
    Activations Density 0.072%

    No Known Activations