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. 0-RES-JB
    6. 7397
    Prev
    Next
    INDEX
    Explanations

    keywords related to land activities, such as "clearing."

    oai_token-act-pair · gpt-3.5-turbo

    instances of "clearing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otypes
    -0.80
     Lives
    -0.76
    olds
    -0.69
    otype
    -0.68
    asio
    -0.67
     Levi
    -0.66
    ongs
    -0.65
    CV
    -0.64
    owan
    -0.64
    iov
    -0.64
    POSITIVE LOGITS
     clearing
    3.93
     clears
    1.67
     cleared
    1.43
     clearance
    1.36
     wiping
    1.32
     cleansing
    1.29
     paving
    1.29
    cle
    1.25
     dumping
    1.24
    Cle
    1.21
    Activations Density 0.017%

    No Known Activations