Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1646
    Prev
    Next
    INDEX
    Explanations

    references to religious figures, particularly related to Christ

    oai_token-act-pair · gpt-3.5-turbo

    references to Christ

    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
    TRY
    -0.79
    phrine
    -0.77
    ãĥ³ãĤ¸
    -0.76
    å§
    -0.74
    IFE
    -0.72
    é¾
    -0.70
    RAW
    -0.69
    ACTION
    -0.69
    ickr
    -0.67
    GMT
    -0.66
    POSITIVE LOGITS
    ophe
    1.24
    church
    1.11
    isphere
    1.04
    mast
    1.03
    esian
    0.98
     Christ
    0.91
    elin
    0.88
    ophers
    0.88
    eson
    0.87
    lia
    0.86
    Activations Density 0.006%

    No Known Activations