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. 7-RES-JB
    6. 9258
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the importance or impact of actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that convey significance or impact

    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
    hops
    -0.87
    iddles
    -0.77
    ifles
    -0.75
     Classes
    -0.73
    aters
    -0.70
    rencies
    -0.68
    lees
    -0.67
     Contracts
    -0.67
    ORTS
    -0.66
    tis
    -0.66
    POSITIVE LOGITS
     impression
    1.00
     foothold
    0.94
     amount
    0.90
     dose
    0.84
     berth
    0.83
     chunk
    0.83
     role
    0.80
     comeback
    0.80
     bead
    0.79
     version
    0.78
    Activations Density 0.252%

    No Known Activations