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. 15959
    Prev
    Next
    INDEX
    Explanations

    article phrases indicating future actions or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    the verb "to be" in various contexts indicating existence or state of affairs

    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
     congratulations
    -0.73
    âĦ¢:
    -0.67
     Relations
    -0.66
    ipeg
    -0.65
     Heights
    -0.64
     Dude
    -0.64
     Benz
    -0.64
     Album
    -0.64
    album
    -0.62
     Anniversary
    -0.62
    POSITIVE LOGITS
     able
    1.23
     spared
    1.12
     harmed
    1.05
     affected
    1.04
     replaced
    1.03
     abolished
    1.03
     impacted
    1.02
     persuaded
    0.99
     eliminated
    0.98
     relocated
    0.98
    Activations Density 0.244%

    No Known Activations