Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 2120
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms specifically related to property rights

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and social issues surrounding abortion and related rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mith
    -0.72
     bye
    -0.68
     Mub
    -0.66
     affirm
    -0.66
     hereby
    -0.66
     ter
    -0.63
     supplemental
    -0.63
     tac
    -0.62
     Valent
    -0.62
     aloud
    -0.61
    POSITIVE LOGITS
    ursed
    1.03
    ortion
    0.96
    ervatives
    0.92
    ament
    0.90
    thal
    0.85
    ammy
    0.84
    isitions
    0.82
    ervative
    0.82
    arde
    0.82
    itures
    0.82
    Activations Density 0.025%

    No Known Activations