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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 8405
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "God."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of God

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lima
    -0.65
     Luxem
    -0.62
     Cheong
    -0.61
    Downloadha
    -0.60
    OUR
    -0.59
     needle
    -0.59
     Morales
    -0.58
     contin
    -0.58
    URRENT
    -0.58
    ROR
    -0.57
    POSITIVE LOGITS
    frey
    1.47
    father
    1.30
    mother
    1.13
    win
    1.10
     bless
    1.08
     forbid
    1.07
     Bless
    1.05
    zilla
    1.05
    olphin
    1.03
    spell
    1.03
    Activations Density 0.044%

    No Known Activations