© 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. 10-RES-JB
    11. 16146
    Prev
    Next
    INDEX
    Explanations

    words related to changes or shifts in a context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a change or shift in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pots
    -0.76
    linger
    -0.73
    ľ
    -0.73
    ongs
    -0.70
    Ĭ
    -0.68
    uge
    -0.68
    NULL
    -0.68
    ¤
    -0.67
    brew
    -0.67
    ŀ
    -0.66
    POSITIVE LOGITS
     attitude
    1.14
     attitudes
    1.10
     terminology
    1.08
     perception
    1.08
     terms
    1.05
     mentality
    1.01
     behaviour
    0.99
     behavior
    0.99
     outlook
    0.99
     mindset
    0.98
    Activations Density 0.103%

    No Known Activations