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. 16216
    Prev
    Next
    INDEX
    Explanations

    verbs related to demonstrating or showcasing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to demonstrating or exhibiting actions and qualities

    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
    etheless
    -0.71
    agher
    -0.64
    nian
    -0.62
    ascus
    -0.62
    etary
    -0.60
     nutshell
    -0.59
     compounded
    -0.59
    assic
    -0.58
     Variant
    -0.58
    ataka
    -0.57
    POSITIVE LOGITS
    ered
    1.03
    alter
    1.00
    manship
    0.98
    biz
    0.98
    runners
    0.89
    runner
    0.77
     Thumbnails
    0.73
    ittal
    0.73
    tek
    0.72
    amy
    0.71
    Activations Density 0.056%

    No Known Activations