© 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. 1-RES-JB
    11. 24179
    Prev
    Next
    INDEX
    Explanations

    words relating to dependence or reliance on something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rely" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milan
    -0.74
     Dian
    -0.73
    jar
    -0.71
     Helsinki
    -0.71
     Mushroom
    -0.69
    Mar
    -0.68
    gran
    -0.67
    vision
    -0.66
    cision
    -0.66
     Kamp
    -0.66
    POSITIVE LOGITS
     rely
    1.26
     relied
    1.25
     relying
    1.02
     relies
    1.01
     reliant
    0.98
     depended
    0.94
    enza
    0.94
     solely
    0.89
    awaru
    0.84
     reliance
    0.83
    Activations Density 0.013%

    No Known Activations