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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 22550
    Prev
    Next
    INDEX
    Explanations

    positive adjectives related to qualities like size, strength, and improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pedia
    -0.66
    alach
    -0.65
    anka
    -0.65
    livious
    -0.63
    ossus
    -0.61
    rets
    -0.61
    uty
    -0.59
    any
    -0.59
    ict
    -0.58
    avorite
    -0.57
    POSITIVE LOGITS
     clearer
    1.55
     wiser
    1.49
     richer
    1.46
     quieter
    1.43
     stronger
    1.43
     healthier
    1.43
     quicker
    1.41
     faster
    1.41
     nicer
    1.37
     smoother
    1.37
    Activations Density 0.476%

    No Known Activations