© 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. 1954
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious figures, specifically priests

    oai_token-act-pair · gpt-3.5-turbo

    references to priests and their roles within various contexts

    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
    upon
    -0.79
    DonaldTrump
    -0.77
    chell
    -0.73
    اÙĦ
    -0.73
    BAT
    -0.71
    ilater
    -0.67
    TING
    -0.66
    oday
    -0.65
     Hemp
    -0.64
    issors
    -0.64
    POSITIVE LOGITS
    esses
    1.56
    ess
    1.19
     priest
    1.16
     priests
    1.07
     exorc
    0.89
     Priest
    0.83
    osate
    0.80
    hood
    0.80
     ordained
    0.79
    ly
    0.77
    Activations Density 0.010%

    No Known Activations