© 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. 19954
    Prev
    Next
    INDEX
    Explanations

    references to the religious figure "Christ"

    oai_token-act-pair · gpt-3.5-turbo

    references to Jesus Christ

    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
    ãĥ³ãĤ¸
    -0.86
    RAW
    -0.74
    phrine
    -0.72
    MENT
    -0.66
    å§
    -0.65
    女
    -0.64
    TRY
    -0.64
    NRS
    -0.63
     Yugoslavia
    -0.62
     slot
    -0.62
    POSITIVE LOGITS
    ophe
    1.14
    church
    1.14
    isphere
    1.07
    mast
    1.03
    esian
    0.97
     Christ
    0.96
    lia
    0.89
    elin
    0.88
    angel
    0.86
    alis
    0.84
    Activations Density 0.006%

    No Known Activations