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. 0-RES-JB
    6. 7109
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fundamentalist groups and their beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingen
    -0.71
    air
    -0.68
    Car
    -0.68
    chairs
    -0.67
    au
    -0.66
    iku
    -0.66
    Gra
    -0.66
    URE
    -0.66
    aste
    -0.65
    lace
    -0.65
    POSITIVE LOGITS
     Fundamental
    3.04
     Semin
    2.26
     fundamentalist
    1.92
     polyg
    1.23
    nery
    1.07
     Witnesses
    1.05
     preacher
    1.05
     polygamy
    1.04
    amous
    1.01
     devout
    0.99
    Activations Density 0.049%

    No Known Activations