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. 21963
    Prev
    Next
    INDEX
    Explanations

    words related to secrecy, manipulation, and hidden information

    oai_token-act-pair · gpt-3.5-turbo

    words related to obscurity and manipulation

    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
    BSD
    -0.74
     Resistance
    -0.71
     Hearts
    -0.71
    WT
    -0.70
    BU
    -0.69
    shapeshifter
    -0.68
     Expend
    -0.68
     Serpent
    -0.67
     Wonderland
    -0.66
     Venture
    -0.66
    POSITIVE LOGITS
    estate
    1.15
    itudes
    1.08
    inations
    1.02
    ications
    1.02
    s
    1.02
    resses
    1.01
    estones
    1.00
    iques
    0.97
    ifications
    0.96
    ues
    0.93
    Activations Density 0.025%

    No Known Activations