© 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. 2-RES-JB
    11. 973
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to silence

    oai_token-act-pair · gpt-3.5-turbo

    the word "silent" regardless of context

    oai_token-act-pair · gpt-4-turbo

    instances of the word "silent" or related concepts surrounding silence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hr
    -0.74
    isin
    -0.73
    MpServer
    -0.73
    ramid
    -0.71
    RAFT
    -0.70
    akeru
    -0.68
    lete
    -0.67
    GPU
    -0.66
    raphics
    -0.66
    ANA
    -0.66
    POSITIVE LOGITS
     silent
    0.93
     bystand
    0.87
     silence
    0.80
     Silence
    0.78
     vigil
    0.78
     seiz
    0.76
     mute
    0.75
     aperture
    0.73
     autom
    0.72
     cooker
    0.72
    Activations Density 0.007%

    No Known Activations