© 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. 11-RES-JB
    11. 21912
    Prev
    Next
    INDEX
    Explanations

    phrases related to predictions or expectations about future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future actions or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -0.74
    olicited
    -0.72
    urus
    -0.71
    Prop
    -0.69
    onian
    -0.66
     hereby
    -0.64
    76561
    -0.63
    osal
    -0.62
    omatic
    -0.61
    ournals
    -0.60
    POSITIVE LOGITS
     tougher
    0.91
     sorely
    0.89
     uphill
    0.83
     interesting
    0.83
     tough
    0.81
     someday
    0.80
     harder
    0.79
     tomorrow
    0.78
     toughest
    0.77
     forever
    0.75
    Activations Density 0.317%

    No Known Activations