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. 1-RES-JB
    6. 15208
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations or entities being below or underneath something else

    oai_token-act-pair · gpt-3.5-turbo

    the word "beneath" and its context, often relating to underlying themes or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yah
    -0.79
    ordan
    -0.74
    ³³³
    -0.70
     Physicians
    -0.69
    Attempts
    -0.68
     Preferred
    -0.67
    Hispanic
    -0.66
    MRI
    -0.66
     Ammo
    -0.66
     STL
    -0.65
    POSITIVE LOGITS
    eatures
    1.12
    ĸļ
    1.06
     tremend
    1.06
    neath
    1.01
     beneath
    0.99
    pins
    0.94
     therap
    0.88
     layers
    0.87
     underneath
    0.85
     veter
    0.84
    Activations Density 0.014%

    No Known Activations