© 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. 11-RES-JB
    11. 9200
    Prev
    Next
    INDEX
    Explanations

    phrases related to completing tasks or projects

    oai_token-act-pair · gpt-3.5-turbo

    references to completing tasks or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srfAttach
    -0.73
    anqu
    -0.70
    amiya
    -0.64
    angers
    -0.64
     Archdemon
    -0.63
     Danger
    -0.63
     Principle
    -0.61
    clude
    -0.59
     disobedience
    -0.59
     Deter
    -0.58
    POSITIVE LOGITS
     done
    1.31
     sorted
    1.25
     figured
    1.08
    done
    1.07
     nailed
    1.06
    started
    1.04
     reinstated
    1.02
     repaired
    1.01
     cleaned
    1.01
     wrong
    1.01
    Activations Density 0.211%

    No Known Activations