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. 11-RES-JB
    6. 4283
    Prev
    Next
    INDEX
    Explanations

    mentions of cults and cult-like followings

    oai_token-act-pair · gpt-3.5-turbo

    references to cults and cult-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.75
    etsk
    -0.73
    sole
    -0.67
    balance
    -0.66
    etter
    -0.65
    ptroller
    -0.61
    Downloadha
    -0.61
     Stra
    -0.60
    CO
    -0.59
     Fowler
    -0.59
    POSITIVE LOGITS
    ivating
    1.41
    ivated
    1.32
    urally
    1.26
    ivation
    1.24
    ures
    1.03
    ishly
    0.99
    ured
    0.99
    ura
    0.98
    atical
    0.97
    urable
    0.94
    Activations Density 0.047%

    No Known Activations