© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 16438
    Prev
    Next
    INDEX
    Explanations

    mentions of proposed laws and legislative actions

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "would" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guessing
    -0.66
    hea
    -0.65
    essing
    -0.65
    standing
    -0.65
    inventoryQuantity
    -0.64
     guesses
    -0.64
    GGGGGGGG
    -0.64
     Gladiator
    -0.63
    noticed
    -0.63
    answered
    -0.62
    POSITIVE LOGITS
     prohibit
    1.28
     authorize
    1.27
     allow
    1.24
     require
    1.23
     impose
    1.20
     eliminate
    1.18
     legalize
    1.16
     deprive
    1.11
     entail
    1.10
     amend
    1.09
    Activations Density 0.094%

    No Known Activations