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. 100
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing guidance or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing the easiest methods or approaches to accomplish tasks

    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
    IT
    -0.53
    AA
    -0.51
    ISS
    -0.51
     serious
    -0.50
    ting
    -0.49
    CE
    -0.49
    vik
    -0.49
    INA
    -0.48
    embed
    -0.47
    than
    -0.47
    POSITIVE LOGITS
     easiest
    3.04
     simplest
    2.55
     quickest
    2.36
     cheapest
    2.26
     safest
    2.18
     shortest
    1.74
     smallest
    1.73
     hardest
    1.69
     happiest
    1.62
    liest
    1.60
    Activations Density 0.013%

    No Known Activations