© 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
    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. 13855
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal convictions or principles

    oai_token-act-pair · gpt-3.5-turbo

    references to religious beliefs

    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
     Mamm
    -0.77
     Amen
    -0.76
    amen
    -0.74
    sg
    -0.74
    hens
    -0.70
    xon
    -0.70
    amaz
    -0.70
    nice
    -0.69
    agher
    -0.69
    othy
    -0.68
    POSITIVE LOGITS
     beliefs
    1.21
     guiActiveUn
    0.92
     belief
    0.88
    linger
    0.87
     prejudices
    0.82
    ieve
    0.80
     biases
    0.78
    iosyncr
    0.77
    edIn
    0.76
     Belief
    0.76
    Activations Density 0.014%

    No Known Activations