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. 6-RES-JB
    6. 3812
    Prev
    Next
    INDEX
    Explanations

    phrases related to activism and social issues

    oai_token-act-pair · gpt-3.5-turbo

    words related to activism and activist actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retreat
    -0.77
    OPLE
    -0.74
    BALL
    -0.74
     breath
    -0.72
     sliding
    -0.69
     Saber
    -0.66
     ECO
    -0.65
     Drake
    -0.65
    HEAD
    -0.65
     halfway
    -0.64
    POSITIVE LOGITS
    ision
    1.21
    icion
    1.21
    iment
    1.07
    imedia
    1.06
    ications
    1.06
    ition
    1.03
    itive
    1.02
    icator
    1.00
    icating
    0.99
    icle
    0.99
    Activations Density 0.043%

    No Known Activations