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. 0-RES-JB
    6. 10903
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "bits"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to digital information or data

    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
     hospital
    -0.75
     sanction
    -0.66
     wound
    -0.65
     cause
    -0.64
     reign
    -0.64
     pest
    -0.63
     domestic
    -0.63
     sed
    -0.63
     title
    -0.62
     Missouri
    -0.61
    POSITIVE LOGITS
    bits
    4.25
     Bits
    1.42
    BIT
    1.23
    pins
    1.03
    bytes
    1.01
    bit
    1.00
    istors
    0.97
    Bytes
    0.95
     bits
    0.93
    uggets
    0.91
    Activations Density 0.025%

    No Known Activations