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. 23713
    Prev
    Next
    INDEX
    Explanations

    phrases indicating expressing opinions or contributions in a discussion or decision-making process

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating involvement or participation in discussions or decisions

    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
    href
    -0.78
    ça
    -0.73
    alysed
    -0.70
    hens
    -0.65
    hent
    -0.64
    rint
    -0.63
     Forgotten
    -0.63
     [+]
    -0.63
    FML
    -0.62
    ovi
    -0.62
    POSITIVE LOGITS
     volumes
    0.70
    culosis
    0.68
     weighing
    0.66
     fists
    0.66
     approving
    0.65
     heaviest
    0.65
     shoulders
    0.65
     weighs
    0.63
     volume
    0.62
     stakes
    0.62
    Activations Density 0.097%

    No Known Activations