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

    Neuronpedia

    APICircuit 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. 1992
    Prev
    Next
    INDEX
    Explanations

    action-oriented phrases related to completing tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to completing tasks or getting things done

    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
    amiya
    -0.67
     disobedience
    -0.66
    anqu
    -0.65
    risk
    -0.63
    angers
    -0.63
    clude
    -0.62
    aths
    -0.60
    eware
    -0.59
    archives
    -0.59
     preferring
    -0.58
    POSITIVE LOGITS
     done
    1.18
     sorted
    1.16
     ready
    1.00
     repaired
    0.99
     wrong
    0.96
     underway
    0.93
     flowing
    0.92
     cleaned
    0.92
     figured
    0.92
     reinstated
    0.91
    Activations Density 0.207%

    No Known Activations