Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3639
    Prev
    Next
    INDEX
    Explanations

    numerical ages and time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to childhood development and early experiences

    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
     Spectre
    -0.78
     bids
    -0.68
     Franch
    -0.66
     Collider
    -0.66
    Contract
    -0.65
    Winner
    -0.65
     RAID
    -0.65
     Bib
    -0.65
     Simmons
    -0.64
     Syndicate
    -0.64
    POSITIVE LOGITS
     adulthood
    1.72
     adolescence
    1.64
     puberty
    1.55
     infancy
    1.40
    uberty
    1.38
     age
    1.29
     childhood
    1.23
     onset
    1.18
     gestation
    1.17
     ages
    1.16
    Activations Density 0.205%

    No Known Activations