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. 3-RES-JB
    6. 22272
    Prev
    Next
    INDEX
    Explanations

    information related to starting or building something from the beginning or from basics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "from scratch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disproportionate
    -0.69
    amide
    -0.68
    ossession
    -0.67
     Ober
    -0.66
    CVE
    -0.64
     heaviest
    -0.63
     Bundes
    -0.61
    agonist
    -0.61
    Iraq
    -0.60
     Palestin
    -0.60
    POSITIVE LOGITS
     scratch
    1.19
    pad
    1.00
    ratch
    0.95
     scratched
    0.92
    manship
    0.88
    berry
    0.82
    beat
    0.81
    lihood
    0.81
    bats
    0.79
     slate
    0.78
    Activations Density 0.013%

    No Known Activations