© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 9960
    Prev
    Next
    INDEX
    Explanations

    business-related sentences specifically focusing on solutions, achievements, and contributions

    oai_token-act-pair · gpt-3.5-turbo

    the word "by" as a significant marker in the context of actions or contributions

    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
    Mine
    -0.71
    OTAL
    -0.71
    atz
    -0.69
    Silver
    -0.68
    igrate
    -0.66
    raq
    -0.65
    Kings
    -0.65
    WER
    -0.64
    hene
    -0.64
    bian
    -0.64
    POSITIVE LOGITS
     virtue
    1.30
     introducing
    1.25
     eliminating
    1.25
     providing
    1.23
     adopting
    1.22
     allowing
    1.21
     combining
    1.21
     removing
    1.21
     creating
    1.19
     bringing
    1.18
    Activations Density 0.090%

    No Known Activations