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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 3944
    Prev
    Next
    INDEX
    Explanations

    phrases related to persuasion or convincing someone of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with persuading or convincing others

    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
    quartered
    -0.79
    ember
    -0.72
     spons
    -0.67
     Municip
    -0.64
    miah
    -0.64
    ¥ŀ
    -0.63
     Unch
    -0.63
    regulated
    -0.63
    option
    -0.62
    arah
    -0.62
    POSITIVE LOGITS
    ments
    1.11
    ingly
    0.99
    ings
    0.85
     him
    0.83
    oshop
    0.83
    tale
    0.81
    imaru
    0.81
    uate
    0.78
    itism
    0.76
    ĸļ
    0.76
    Activations Density 0.032%

    No Known Activations