Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16035
    Prev
    Next
    INDEX
    Explanations

    verbs related to giving or granting permission

    oai_token-act-pair · gpt-3.5-turbo

    the word "issue" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asia
    -0.80
    bered
    -0.78
    uton
    -0.76
    tes
    -0.75
     destro
    -0.73
    bsite
    -0.73
    sle
    -0.72
    uphem
    -0.70
    ombo
    -0.69
    apy
    -0.68
    POSITIVE LOGITS
     certificates
    0.75
     advis
    0.75
     citations
    0.74
    iates
    0.73
     refunds
    0.71
    iate
    0.69
    iating
    0.66
     rulings
    0.66
     forth
    0.64
     Statement
    0.64
    Activations Density 0.032%

    No Known Activations