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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 1667
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious beliefs

    oai_token-act-pair · gpt-3.5-turbo

    references to beliefs and their implications

    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
    ptives
    -0.74
    neau
    -0.70
    cephal
    -0.66
    Delivery
    -0.66
    fac
    -0.63
    Naz
    -0.62
    ded
    -0.62
    BUG
    -0.62
    othy
    -0.61
    sg
    -0.61
    POSITIVE LOGITS
    linger
    1.06
    mith
    0.94
    hips
    0.92
    ettings
    0.89
    omething
    0.88
    cape
    0.85
     beliefs
    0.85
    ynski
    0.85
    uits
    0.85
    hip
    0.84
    Activations Density 0.059%

    No Known Activations