© 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. 7-RES-JB
    11. 16788
    Prev
    Next
    INDEX
    Explanations

    words related to breathing or inhalation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inhalation and exhalation, often in the context of respiratory issues or sensations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Templar
    -0.76
    Corp
    -0.72
     Revival
    -0.70
     Payton
    -0.66
     Cla
    -0.65
     Telegram
    -0.64
     Chow
    -0.63
     Spawn
    -0.63
     Colonial
    -0.63
     Construct
    -0.62
    POSITIVE LOGITS
    ospital
    1.11
    aled
    1.08
     inh
    1.03
     exh
    0.93
    ogens
    0.88
    osp
    0.86
    uming
    0.84
    uls
    0.84
    avored
    0.83
    reath
    0.82
    Activations Density 0.051%

    No Known Activations