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. 14754
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Blair" along with various other references in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities related to "Blair."

    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
    Magikarp
    -0.98
    ymes
    -0.83
    entric
    -0.79
    uality
    -0.79
    ktop
    -0.73
    Ģ
    -0.72
    Temperature
    -0.72
    ensing
    -0.71
    Arizona
    -0.71
    Roaming
    -0.69
    POSITIVE LOGITS
     Blair
    0.96
    umenthal
    0.86
    anke
    0.82
    ouncing
    0.80
    ites
    0.77
    abies
    0.75
    icus
    0.75
    ock
    0.75
    jamin
    0.75
    anche
    0.75
    Activations Density 0.014%

    No Known Activations