© 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. 13728
    Prev
    Next
    INDEX
    Explanations

    phrases related to various influencing factors or causes in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various factors and their impacts in different 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
    «ĺ
    -0.76
    à¼
    -0.74
    emonium
    -0.71
    rr
    -0.69
    =-=-=-=-
    -0.67
    aris
    -0.67
    SY
    -0.67
    rss
    -0.67
    unes
    -0.66
     Frie
    -0.65
    POSITIVE LOGITS
     varying
    0.98
     determining
    0.91
     success
    0.86
     differing
    0.83
     including
    0.82
     interpreting
    0.80
    iating
    0.80
     evaluating
    0.79
     implementing
    0.78
     achieving
    0.78
    Activations Density 0.311%

    No Known Activations