© 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. 3-RES-JB
    6. 22720
    Prev
    Next
    INDEX
    Explanations

    the name "Ren" with varying degrees of strength

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ren" in various contexts

    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
    stakes
    -0.92
    milo
    -0.79
    OOL
    -0.76
    HAEL
    -0.74
    trak
    -0.73
    Ö¼
    -0.72
     Samoa
    -0.68
     mileage
    -0.68
     Antar
    -0.68
     Bermuda
    -0.67
    POSITIVE LOGITS
    unciation
    1.04
    issance
    1.04
    unci
    1.01
    ovation
    0.97
    semble
    0.93
    owned
    0.88
    ners
    0.88
    ault
    0.87
    emy
    0.87
    Ren
    0.87
    Activations Density 0.007%

    No Known Activations