© 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. 0-RES-JB
    11. 6227
    Prev
    Next
    INDEX
    Explanations

    phrases related to the widespread distribution of information or rumors

    oai_token-act-pair · gpt-3.5-turbo

    words related to the act of spreading information or rumors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anthrop
    -0.70
     Ellie
    -0.68
     Tree
    -0.68
     Bash
    -0.65
    ppo
    -0.65
    cmd
    -0.64
     Gods
    -0.64
    Query
    -0.63
     paradigm
    -0.63
    ines
    -0.63
    POSITIVE LOGITS
     circulating
    3.47
     circulated
    3.40
     circulate
    3.20
     circulation
    1.57
     circ
    1.55
     dissemin
    1.47
     floated
    1.46
     surfaced
    1.42
     forwarded
    1.22
     leaked
    1.17
    Activations Density 0.028%

    No Known Activations