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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 15126
    Prev
    Next
    INDEX
    Explanations

    mentions of speculation or rumors

    oai_token-act-pair · gpt-3.5-turbo

    instances of speculation or conjecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nea
    -0.78
    oho
    -0.77
    ī
    -0.77
    ophon
    -0.77
    Ģ
    -0.76
    itu
    -0.74
    ĺħ
    -0.72
    ĭ
    -0.69
    tha
    -0.67
    ĪĴ
    -0.66
    POSITIVE LOGITS
     conjecture
    0.88
     speculate
    0.87
    ulations
    0.84
     speculation
    0.81
     regarding
    0.77
     theories
    0.76
     about
    0.76
     rumours
    0.75
     conject
    0.75
     whether
    0.73
    Activations Density 0.061%

    No Known Activations