© 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. 10-RES-JB
    11. 5021
    Prev
    Next
    INDEX
    Explanations

    verbs in command or instructional format

    oai_token-act-pair · gpt-3.5-turbo

    policy and governance-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typo
    -0.78
     Wer
    -0.70
     Ars
    -0.69
     Stam
    -0.67
     Pry
    -0.66
     Funny
    -0.66
     Buzz
    -0.65
     Rusty
    -0.65
     Dawson
    -0.64
     goof
    -0.64
    POSITIVE LOGITS
     fost
    0.91
     segreg
    0.85
     incentiv
    0.84
    Allow
    0.82
     prohibits
    0.81
    ·
    0.79
     nurt
    0.78
    restricted
    0.77
    exempt
    0.76
     prohibit
    0.76
    Activations Density 0.620%

    No Known Activations