Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6829
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions occurring at a specific time or along with other actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "while" in various contexts, indicating actions or events that occur simultaneously

    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
    ilial
    -0.78
    elled
    -0.77
    urable
    -0.71
    oux
    -0.71
    hack
    -0.71
    illet
    -0.70
    ][/
    -0.70
    iotic
    -0.70
    urated
    -0.70
    omorphic
    -0.70
    POSITIVE LOGITS
     awaiting
    1.30
     researching
    1.16
     waiting
    1.13
     retaining
    1.09
     traveling
    1.09
     maintaining
    1.08
     conducting
    1.06
     attempting
    1.06
     undergoing
    1.05
     preparing
    1.05
    Activations Density 0.062%

    No Known Activations