© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7114
    Prev
    Next
    INDEX
    Explanations

    references to the mineral "asbestos"

    oai_token-act-pair · gpt-3.5-turbo

    references to asbestos and its related health risks

    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
    ndra
    -1.01
    fare
    -0.94
    quarter
    -0.91
    fruit
    -0.84
    eteen
    -0.79
    hyde
    -0.79
    eling
    -0.79
    ety
    -0.77
    ju
    -0.77
    sword
    -0.77
    POSITIVE LOGITS
    д
    0.83
    IONS
    0.77
     CLIENT
    0.69
     LIA
    0.68
    ION
    0.68
    ITNESS
    0.67
    ions
    0.67
     PROT
    0.67
    ISON
    0.63
     coalition
    0.62
    Activations Density 0.028%

    No Known Activations