Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 23179
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions that involve making, modifying, adjusting, changing, assembling, using, manipulating, controlling, applying, and solving

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to processes and actions that imply creation, modification, or application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Berk
    -0.65
     Dracula
    -0.62
     Cah
    -0.61
     Suffolk
    -0.60
     Horton
    -0.59
     Alc
    -0.58
    dan
    -0.57
     gotta
    -0.56
     clipboard
    -0.55
     Phi
    -0.55
    POSITIVE LOGITS
     easily
    1.06
     safely
    1.00
     cheaply
    0.94
     anytime
    0.90
     alternatively
    0.90
     manually
    0.89
     offline
    0.87
     anywhere
    0.84
     arbitrarily
    0.84
     separately
    0.81
    Activations Density 0.148%

    No Known Activations