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. 11-RES-JB
    6. 15428
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "sing" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Sing" or its variations in relation to music or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stur
    -0.67
     grip
    -0.61
    pora
    -0.60
     hunger
    -0.59
     creation
    -0.58
    IVES
    -0.58
     VICE
    -0.57
     overflow
    -0.56
     tire
    -0.56
     fuel
    -0.56
    POSITIVE LOGITS
    apore
    1.89
    ularity
    1.82
    leton
    1.37
    leness
    1.31
    ular
    1.28
    lish
    1.17
    lest
    1.14
    les
    1.11
    along
    1.10
    lez
    1.01
    Activations Density 0.047%

    No Known Activations