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. 7-RES-JB
    6. 6661
    Prev
    Next
    INDEX
    Explanations

    proper names related to the name "Nikita"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "Nik."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LOAD
    -0.76
    GROUND
    -0.75
    ARDS
    -0.69
    fare
    -0.67
     marrow
    -0.66
    BACK
    -0.65
    ä¹ĭ
    -0.65
    ARD
    -0.64
    20439
    -0.64
     SPORTS
    -0.63
    POSITIVE LOGITS
    aido
    1.27
    ita
    1.09
    opol
    1.07
    ola
    0.99
    eties
    0.99
    olas
    0.97
    orius
    0.97
    seys
    0.97
    emic
    0.95
    umar
    0.94
    Activations Density 0.032%

    No Known Activations