© 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. 1-RES-JB
    11. 16396
    Prev
    Next
    INDEX
    Explanations

    phrases related to pharmaceutical drugs or medical substances

    oai_token-act-pair · gpt-3.5-turbo

    references to the drug "phenmetrazine" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITED
    -0.83
    glers
    -0.80
    ITAL
    -0.72
     DISTRICT
    -0.69
    yrinth
    -0.69
    din
    -0.68
    ^^^^
    -0.64
     Ministry
    -0.64
    displayText
    -0.63
     Federal
    -0.63
    POSITIVE LOGITS
    otyp
    1.21
    phen
    1.10
    otypes
    1.02
    ographically
    0.96
    oses
    0.92
    ographic
    0.91
    osis
    0.90
    ophon
    0.89
    acid
    0.86
    ophen
    0.83
    Activations Density 0.010%

    No Known Activations