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. 16911
    Prev
    Next
    INDEX
    Explanations

    adjectives related to physical qualities or abilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming mechanics and strategies

    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
    angered
    -0.64
    ndum
    -0.59
    ̶
    -0.52
    Merit
    -0.52
     BuzzFeed
    -0.50
    realDonaldTrump
    -0.50
    Brexit
    -0.49
     embattled
    -0.49
     Trayvon
    -0.49
    SPONSORED
    -0.49
    POSITIVE LOGITS
     is
    1.23
     consists
    1.22
     includes
    1.22
     retains
    1.18
     tends
    1.17
     comprises
    1.16
     ensures
    1.15
     refers
    1.14
     utilizes
    1.14
     incorporates
    1.14
    Activations Density 0.891%

    No Known Activations