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. 10377
    Prev
    Next
    INDEX
    Explanations

    words related to renaming or nationalizing

    oai_token-act-pair · gpt-3.5-turbo

    words related to renaming or rebranding

    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
    ramid
    -0.80
     Pend
    -0.78
    aneers
    -0.76
     Hemp
    -0.71
     McGee
    -0.70
     Pike
    -0.68
    intendent
    -0.66
     Samoa
    -0.65
    stakes
    -0.65
    HAEL
    -0.64
    POSITIVE LOGITS
    unci
    1.29
    unciation
    1.20
     ren
    1.00
    ouncing
    0.95
    naissance
    0.93
    aming
    0.92
    ounced
    0.91
    esis
    0.89
    etics
    0.88
    upt
    0.88
    Activations Density 0.005%

    No Known Activations