© 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. 4-RES-JB
    11. 9743
    Prev
    Next
    INDEX
    Explanations

    words related to various drugs and medication

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms in the document

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

    No Comments

    Negative Logits
    ĸļ
    -0.98
     Amend
    -0.79
    Ô
    -0.76
     curtains
    -0.75
     derog
    -0.68
     footing
    -0.67
    eers
    -0.67
    eele
    -0.62
    ONSORED
    -0.62
    raviolet
    -0.62
    POSITIVE LOGITS
    opter
    0.95
    adelphia
    0.94
    ebus
    0.88
    ashtra
    0.85
    aceutical
    0.81
    eric
    0.79
    ogram
    0.78
    Ļ
    0.78
    alon
    0.76
    icians
    0.74
    Activations Density 0.104%

    No Known Activations