© 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. 4-RES-JB
    11. 20773
    Prev
    Next
    INDEX
    Explanations

    terms related to protection of intellectual property or classes covered by law protection

    oai_token-act-pair · gpt-3.5-turbo

    references to legal protections and rights

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

    No Comments

    Negative Logits
    bender
    -0.87
    ellen
    -0.70
    hur
    -0.68
     Cra
    -0.67
    bang
    -0.66
    hun
    -0.66
    EEK
    -0.64
    wow
    -0.64
    hower
    -0.64
    elia
    -0.64
    POSITIVE LOGITS
     protected
    0.98
     anonymity
    0.83
     protects
    0.82
     protecting
    0.80
     unprotected
    0.80
     shielded
    0.76
    ected
    0.75
     safegu
    0.74
    igion
    0.74
     guardians
    0.73
    Activations Density 0.024%

    No Known Activations