© 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. 10-RES-JB
    11. 12863
    Prev
    Next
    INDEX
    Explanations

    phrases relating to persuasion or influencing others to do something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to" followed by various actions or events

    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
    Compar
    -0.71
    runtime
    -0.71
    umerable
    -0.64
     inferred
    -0.64
     speculation
    -0.61
     estimated
    -0.61
    orically
    -0.61
    awan
    -0.61
    gross
    -0.61
     Chall
    -0.60
    POSITIVE LOGITS
     cooperate
    1.27
     obey
    1.16
     agree
    1.14
     surrender
    1.12
     accept
    1.12
     behave
    1.07
     comply
    1.05
     commit
    1.04
     acquies
    1.03
     relent
    1.02
    Activations Density 0.162%

    No Known Activations