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. 7-RES-JB
    6. 22169
    Prev
    Next
    INDEX
    Explanations

    mentions of cults or cult-like followings

    oai_token-act-pair · gpt-3.5-turbo

    references to cults and their influence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.73
    deen
    -0.71
     Drawn
    -0.62
    lag
    -0.61
     Lag
    -0.57
    cknowled
    -0.57
     Jav
    -0.57
     Stra
    -0.56
     Turk
    -0.56
    Kay
    -0.56
    POSITIVE LOGITS
    ivated
    1.10
    ivating
    1.08
    urally
    1.04
    ivation
    1.02
    ists
    0.98
    ogenic
    0.96
    ura
    0.90
    ures
    0.89
    urable
    0.89
    etic
    0.87
    Activations Density 0.035%

    No Known Activations