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. 4155
    Prev
    Next
    INDEX
    Explanations

    references to the Indian space agency, "Chandrayaan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or entities, particularly variations of the name "Chand"

    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
    istered
    -0.79
    andise
    -0.79
    isons
    -0.72
     Territories
    -0.71
    DIT
    -0.70
    ADE
    -0.69
    cean
    -0.67
    Tube
    -0.66
    umenthal
    -0.66
    ISTER
    -0.66
    POSITIVE LOGITS
    enhagen
    0.97
    »Ĵ
    0.95
    rab
    0.92
    nis
    0.90
    borgh
    0.90
    ership
    0.87
    enberg
    0.78
    nam
    0.77
    erey
    0.75
    lies
    0.74
    Activations Density 0.036%

    No Known Activations