© 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. 563
    Prev
    Next
    INDEX
    Explanations

    verbs related to listening or hearing

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "hears" in various contexts

    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
    olutions
    -0.71
    Transform
    -0.67
     transition
    -0.65
    ynthesis
    -0.64
    DEM
    -0.64
     finish
    -0.64
     resize
    -0.64
    sis
    -0.64
    MO
    -0.63
     checkout
    -0.63
    POSITIVE LOGITS
     hears
    3.33
     circumst
    1.65
     anecdotal
    1.37
     gossip
    1.35
     rumor
    1.27
     slander
    1.24
     anecdote
    1.23
    ecd
    1.22
     conjecture
    1.22
     anecdotes
    1.17
    Activations Density 0.037%

    No Known Activations