© 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. 7-RES-JB
    11. 3045
    Prev
    Next
    INDEX
    Explanations

    items or objects of value or importance in contexts of theft or protection

    oai_token-act-pair · gpt-3.5-turbo

    references to stolen or valuable items

    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
    onomous
    -0.74
    erate
    -0.70
     valleys
    -0.70
    iannopoulos
    -0.67
     resort
    -0.67
    ythm
    -0.66
     zones
    -0.65
     resorts
    -0.65
    ationally
    -0.65
     optimizing
    -0.65
    POSITIVE LOGITS
     confiscated
    1.15
     stored
    1.05
     stash
    1.04
     trove
    1.00
     smuggled
    1.00
     stolen
    0.97
     deposited
    0.97
     donated
    0.97
     belongings
    0.95
     containing
    0.92
    Activations Density 1.337%

    No Known Activations