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. 6-RES-JB
    6. 15644
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to biblical references or biblical figures

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Lev" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.81
    REDACTED
    -0.66
    landish
    -0.66
    roads
    -0.65
    ModLoader
    -0.64
    ãĥĥãĥĪ
    -0.63
    GROUND
    -0.62
     Columb
    -0.61
    stress
    -0.61
    ndum
    -0.58
    POSITIVE LOGITS
    itic
    1.42
    itating
    1.23
    isions
    1.21
    itated
    1.20
    itate
    1.20
    itation
    1.13
    antine
    1.13
    inson
    1.09
    itt
    1.08
    andowski
    1.06
    Activations Density 0.015%

    No Known Activations