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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13328
    Prev
    Next
    INDEX
    Explanations

    phrases related to tasks or responsibilities that need to be completed

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of work and effort

    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
    igmat
    -0.74
    azine
    -0.67
     Higher
    -0.65
    ipolar
    -0.64
     shock
    -0.63
     disbelief
    -0.63
     subscrib
    -0.62
    inately
    -0.61
    anguage
    -0.60
    ounter
    -0.60
    POSITIVE LOGITS
     done
    1.48
     performed
    1.23
    done
    1.19
     undertaken
    1.17
     undone
    1.13
     Done
    1.08
     accomplished
    1.07
     expended
    1.02
     completed
    0.99
     underway
    0.93
    Activations Density 0.146%

    No Known Activations