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. 17188
    Prev
    Next
    INDEX
    Explanations

    phrases related to deception or fraud

    oai_token-act-pair · gpt-3.5-turbo

    words related to states of being or emotional conditions

    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
     frag
    -0.69
     Sinai
    -0.64
     Du
    -0.63
     refin
    -0.63
     persu
    -0.63
    ship
    -0.60
     behind
    -0.59
     upgrading
    -0.59
     than
    -0.58
     stamp
    -0.58
    POSITIVE LOGITS
    oked
    4.43
    okes
    1.78
    oke
    1.60
    oking
    1.27
    okers
    1.21
    oker
    1.18
    oks
    1.14
    ocative
    1.11
    ocated
    1.05
    oled
    1.05
    Activations Density 0.007%

    No Known Activations