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. 11890
    Prev
    Next
    INDEX
    Explanations

    phrases related to astronomical objects and events, specifically focusing on the Milky Way galaxy

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms related to astronomy or celestial objects

    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
    -+-+
    -0.72
    ãĤ©
    -0.71
     conflic
    -0.70
    NECT
    -0.68
    ãĤ¦
    -0.65
    rar
    -0.64
     actionGroup
    -0.64
    ij士
    -0.64
    OTT
    -0.63
     exha
    -0.63
    POSITIVE LOGITS
    hedon
    0.74
    ught
    0.74
    pour
    0.64
    's
    0.61
     dashed
    0.58
    âĦ¢
    0.58
    Leaks
    0.57
     fame
    0.56
    hedral
    0.56
    soever
    0.56
    Activations Density 0.264%

    No Known Activations