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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22484
    Prev
    Next
    INDEX
    Explanations

    phrases related to living spaces like dormitories

    oai_token-act-pair · gpt-3.5-turbo

    references to living accommodations or housing arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAY
    -0.67
     decisive
    -0.61
     Zimbabwe
    -0.60
    ++++++++++++++++
    -0.60
    SHIP
    -0.59
    EStream
    -0.59
     delegated
    -0.59
     undone
    -0.59
     Belarus
    -0.59
     Mehran
    -0.59
    POSITIVE LOGITS
    itory
    1.58
    ancy
    1.16
    ysis
    1.10
    ulty
    1.05
    uates
    1.02
    iott
    1.02
    iencies
    0.98
    mers
    0.97
     dorm
    0.93
    itary
    0.89
    Activations Density 0.012%

    No Known Activations