Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 2990
    Prev
    Next
    INDEX
    Explanations

    the word "adaptation" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "adaptation" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    board
    -0.74
    rooms
    -0.74
    âĸ¬
    -0.73
    002
    -0.72
    rollers
    -0.70
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.70
     Vall
    -0.70
    mu
    -0.70
    gun
    -0.69
    mouth
    -0.65
    POSITIVE LOGITS
     adaptation
    1.29
    adapt
    1.11
     adaptations
    1.09
     Adapt
    1.04
     adapted
    1.02
     adapting
    0.94
     adapt
    0.85
     screenplay
    0.85
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.79
    itals
    0.78
    Activations Density 0.007%

    No Known Activations