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. 4-RES-JB
    6. 15169
    Prev
    Next
    INDEX
    Explanations

    phrases related to emphasizing or arguing a point

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "point of view" or perspective

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

    No Comments

    Negative Logits
    apons
    -0.85
    sbm
    -0.72
    apon
    -0.70
    é¾
    -0.70
    UF
    -0.68
    MSN
    -0.67
    thia
    -0.66
    ////////////////
    -0.62
    ################
    -0.62
    LOG
    -0.62
    POSITIVE LOGITS
    ention
    0.74
     differentiation
    0.73
     rupture
    0.68
    chery
    0.67
     divergence
    0.67
     attack
    0.67
     deletion
    0.66
     convergence
    0.66
     descent
    0.66
     collision
    0.66
    Activations Density 0.149%

    No Known Activations