© 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. 13495
    Prev
    Next
    INDEX
    Explanations

    phrases related to differences or variations

    oai_token-act-pair · gpt-3.5-turbo

    references to diversity or differences in various contexts

    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
    Ĥ
    -0.71
     earnest
    -0.69
    isman
    -0.67
    ª
    -0.66
    ©
    -0.63
    WARN
    -0.62
     excess
    -0.61
     omission
    -0.60
    advertising
    -0.60
     understatement
    -0.59
    POSITIVE LOGITS
     depending
    1.28
     different
    1.22
     differing
    1.22
    Different
    1.14
     Different
    1.09
    different
    1.08
     differently
    1.05
    styles
    0.98
     styles
    0.98
     varying
    0.96
    Activations Density 0.338%

    No Known Activations