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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 10322
    Prev
    Next
    INDEX
    Explanations

    mentions of the chemical compound "phenom" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    vocabulary related to specific names and terms associated with phenomena or individuals

    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
    PDATE
    -0.64
    ETF
    -0.58
    enhagen
    -0.56
    cientious
    -0.56
     trenches
    -0.55
    INA
    -0.55
     breath
    -0.53
    cffff
    -0.53
     gobl
    -0.53
     confessions
    -0.53
    POSITIVE LOGITS
     Hera
    0.58
    oqu
    0.56
    fil
    0.55
     Royale
    0.53
    plain
    0.52
    å§
    0.51
     Defeat
    0.50
    ciating
    0.50
     Gaul
    0.50
     Jinn
    0.49
    Activations Density 1.088%

    No Known Activations