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. 3919
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of place, location, or positioning

    oai_token-act-pair · gpt-3.5-turbo

    words and variations related to "place" or "placing"

    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
    VAL
    -0.66
    SOURCE
    -0.60
    NESS
    -0.60
    USER
    -0.60
     retribution
    -0.58
     macro
    -0.58
     STATS
    -0.58
     reconciliation
    -0.57
     Bash
    -0.57
    ÄŁ
    -0.55
    POSITIVE LOGITS
    ements
    1.49
    ename
    1.20
    ental
    1.13
    ational
    1.08
    idity
    1.06
    estone
    1.03
    atable
    1.03
    amental
    1.01
    emark
    0.97
    emate
    0.96
    Activations Density 0.023%

    No Known Activations