© 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. 4-RES-JB
    11. 15241
    Prev
    Next
    INDEX
    Explanations

    words related to adaptability or being able to adjust to different situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "adapt" and related forms

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

    No Comments

    Negative Logits
    $$$$
    -0.90
    holder
    -0.73
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.72
    Jr
    -0.68
    holders
    -0.67
    âĸ¬
    -0.67
    haul
    -0.66
    govtrack
    -0.66
    TPS
    -0.66
    ++++++++++++++++
    -0.65
    POSITIVE LOGITS
    adapt
    0.88
     adapted
    0.87
    ively
    0.86
     Adapt
    0.86
    ability
    0.83
     adapt
    0.81
     adapting
    0.81
     adaptation
    0.77
    atile
    0.77
    ibility
    0.75
    Activations Density 0.017%

    No Known Activations