© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 9469
    Prev
    Next
    INDEX
    Explanations

    instances of the word "adapt" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    the concept of adaptation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORE
    -0.75
    Jr
    -0.75
    mouth
    -0.74
    clamation
    -0.72
    holder
    -0.72
    jas
    -0.69
    rollers
    -0.69
    llah
    -0.67
    DOWN
    -0.67
    cas
    -0.67
    POSITIVE LOGITS
    ability
    0.91
    adapt
    0.89
     Adapt
    0.88
     adapted
    0.86
    ively
    0.86
     adapt
    0.83
     adapting
    0.80
     adaptation
    0.77
    ably
    0.77
     screenplay
    0.76
    Activations Density 0.029%

    No Known Activations