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. 10-RES-JB
    6. 9618
    Prev
    Next
    INDEX
    Explanations

    complex words or concepts related to human behaviors and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to basic human instincts and their impact on behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.95
    çīĪ
    -0.94
    RAM
    -0.91
    daq
    -0.90
    iHUD
    -0.87
    DAQ
    -0.84
    Legend
    -0.80
    ãĥķãĤ©
    -0.80
    ãĥĩ
    -0.78
    DragonMagazine
    -0.78
    POSITIVE LOGITS
     individuals
    1.44
     humans
    1.41
     males
    1.35
     men
    1.31
     adolescents
    1.28
     adulthood
    1.26
     infants
    1.25
     mankind
    1.25
     adults
    1.24
     humankind
    1.21
    Activations Density 0.386%

    No Known Activations