© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 4302
    Prev
    Next
    INDEX
    Explanations

    references to protective measures or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to protective measures or effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zig
    -0.81
    avez
    -0.81
    licks
    -0.79
    quart
    -0.74
    Daily
    -0.70
    kers
    -0.69
    orne
    -0.68
    Chance
    -0.68
    gd
    -0.67
    ones
    -0.66
    POSITIVE LOGITS
     Protective
    1.06
     protective
    1.01
    ective
    0.88
     shielding
    0.85
     shield
    0.82
     shields
    0.82
     enclosure
    0.80
     protection
    0.79
     encl
    0.78
    adoes
    0.76
    Activations Density 0.010%

    No Known Activations