© 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
    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. 14475
    Prev
    Next
    INDEX
    Explanations

    words related to metal corrosion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to corrosion and metal properties

    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
    zee
    -0.86
    spell
    -0.78
    itia
    -0.76
    ort
    -0.74
    estamp
    -0.73
    whatever
    -0.73
    itar
    -0.72
    essed
    -0.72
    ctors
    -0.71
     Hod
    -0.70
    POSITIVE LOGITS
     alloy
    1.26
     oxide
    1.25
     metals
    1.19
     coating
    0.95
     thickness
    0.91
     molten
    0.88
     electroly
    0.86
     melted
    0.86
    £ı
    0.86
     abras
    0.84
    Activations Density 0.024%

    No Known Activations