© 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. 9-RES-JB
    11. 9864
    Prev
    Next
    INDEX
    Explanations

    phrases related to planned actions or strategies

    oai_token-act-pair · gpt-3.5-turbo

    articles and phrases indicating attempts or endeavors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izons
    -0.76
    omever
    -0.72
    alions
    -0.71
     Egyptians
    -0.64
    onents
    -0.63
    aughter
    -0.61
    ences
    -0.61
    ouls
    -0.60
    utters
    -0.60
    iciency
    -0.59
    POSITIVE LOGITS
     bid
    1.06
     effort
    0.99
     nutshell
    0.94
     attempt
    0.94
    stakes
    0.90
     reversal
    0.89
     testament
    0.85
     unprecedented
    0.84
     manner
    0.84
     ploy
    0.83
    Activations Density 0.217%

    No Known Activations