© 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. 9-RES-JB
    11. 1840
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "managed" indicating accomplishment or successful achievement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "managed" in various contexts

    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
    icipated
    -0.68
    origin
    -0.68
    ibliography
    -0.65
    çīĪ
    -0.63
    osate
    -0.63
    hair
    -0.62
    wi
    -0.61
    inition
    -0.61
    enegger
    -0.60
    RNA
    -0.60
    POSITIVE LOGITS
     toget
    0.76
    cha
    0.72
     to
    0.69
     manage
    0.68
    bably
    0.67
     miser
    0.67
    ité
    0.66
     valiant
    0.65
     unsuccessfully
    0.64
     affairs
    0.63
    Activations Density 0.031%

    No Known Activations