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. 14233
    Prev
    Next
    INDEX
    Explanations

    words related to establishments or locations, especially those ending with "-porium"

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of establishments or venues, particularly those associated with food or entertainment

    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
     unchecked
    -0.72
    ategory
    -0.70
     Skydragon
    -0.62
     whiff
    -0.56
     heed
    -0.56
     toget
    -0.55
     hint
    -0.54
     estrogen
    -0.53
     Sigma
    -0.52
     tacit
    -0.52
    POSITIVE LOGITS
    uments
    0.98
    acements
    0.97
    ciating
    0.87
    culated
    0.86
    rium
    0.85
    brance
    0.81
    oleon
    0.81
    azon
    0.80
    matical
    0.80
    aneous
    0.78
    Activations Density 0.042%

    No Known Activations