© 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. 3741
    Prev
    Next
    INDEX
    Explanations

    mentions of various forms of 'protection'

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of protection

    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
    bold
    -0.80
    ãĥ£
    -0.75
    mers
    -0.65
    RM
    -0.65
    umo
    -0.63
     slightest
    -0.59
    apter
    -0.59
    nexus
    -0.59
    LINE
    -0.58
    sonian
    -0.58
    POSITIVE LOGITS
    ively
    0.98
     afforded
    0.96
    iveness
    0.92
    folios
    0.84
    ously
    0.83
    orship
    0.83
     racket
    0.79
    dogs
    0.79
    aments
    0.77
    itely
    0.76
    Activations Density 0.049%

    No Known Activations