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. 10-RES-JB
    6. 13473
    Prev
    Next
    INDEX
    Explanations

    phrases related to doing something for a specific purpose or duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express actions or sentiments done for others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    operated
    -0.69
    iasco
    -0.66
    gars
    -0.65
    glers
    -0.65
    atars
    -0.65
    abis
    -0.64
    atories
    -0.64
    ering
    -0.64
    quartered
    -0.62
    arts
    -0.62
    POSITIVE LOGITS
     awhile
    1.18
     breakfast
    1.04
    got
    1.02
     lunch
    1.00
     example
    0.99
     fun
    0.99
     reasons
    0.94
     instance
    0.94
     dinner
    0.93
     supper
    0.91
    Activations Density 0.128%

    No Known Activations