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. 8-RES-JB
    6. 8914
    Prev
    Next
    INDEX
    Explanations

    phrases related to the establishment of physical locations or facilities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" and its context related to locations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accounted
    -0.82
    catentry
    -0.78
     tallied
    -0.72
    casters
    -0.71
    mask
    -0.70
     wielded
    -0.69
    runners
    -0.66
    tar
    -0.63
     lodged
    -0.63
     wore
    -0.61
    POSITIVE LOGITS
    efficiency
    0.98
     lieu
    0.97
     vitro
    0.93
    effic
    0.92
     situ
    0.91
     Bangalore
    0.87
     conjunction
    0.85
     Chattanooga
    0.84
     accordance
    0.83
     Cincinnati
    0.79
    Activations Density 0.308%

    No Known Activations