© 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. 0-RES-JB
    11. 11592
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of adapting or adaptive behavior

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to the concept of adaptation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Corpus
    -0.85
     Booth
    -0.69
     Planned
    -0.67
    owed
    -0.66
     birthday
    -0.66
    lees
    -0.65
    wrong
    -0.63
     altar
    -0.63
     misdemeanor
    -0.60
    while
    -0.60
    POSITIVE LOGITS
     adapt
    3.75
     adapting
    2.50
    adapt
    2.22
    Adapt
    2.18
     adapted
    2.15
     Adapt
    2.15
     adaptation
    2.04
     adaptations
    1.91
     adjust
    1.53
     adaptive
    1.42
    Activations Density 0.036%

    No Known Activations