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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 14337
    Prev
    Next
    INDEX
    Explanations

    questions, particularly at the end of declarative statements

    oai_token-act-pair · gpt-3.5-turbo

    temporal references and sequences related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adian
    -0.71
    iosyncr
    -0.70
    ulnerable
    -0.69
    ebted
    -0.65
    ocative
    -0.65
    ãģį
    -0.62
    omics
    -0.62
     poses
    -0.61
    âĦ¢
    -0.61
    born
    -0.61
    POSITIVE LOGITS
     Korra
    0.77
     Luffy
    0.75
     organisers
    0.74
     THEY
    0.73
     they
    0.72
     Zhou
    0.72
     Dumbledore
    0.71
     nobody
    0.71
     Speedway
    0.71
    upon
    0.70
    Activations Density 1.002%

    No Known Activations