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. 8471
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Thorndike"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Thorndike" and its variations or associations

    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
     Wizard
    -0.65
     Bab
    -0.65
     recapt
    -0.60
     correctly
    -0.60
     Doctors
    -0.59
     crystall
    -0.59
     transc
    -0.59
     successfully
    -0.59
     narc
    -0.58
     diff
    -0.57
    POSITIVE LOGITS
    ike
    4.81
    ikes
    2.90
    iking
    2.07
    iked
    1.87
    iker
    1.54
    ikers
    1.48
    icy
    1.39
    iko
    1.23
    icycle
    1.21
    ichael
    1.17
    Activations Density 0.012%

    No Known Activations