© 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. 8-RES-JB
    11. 9453
    Prev
    Next
    INDEX
    Explanations

    phrases related to cost or value

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" and its significance in specifying context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onis
    -0.69
    items
    -0.67
    FTWARE
    -0.66
    ATURES
    -0.66
     transcripts
    -0.66
     Tayyip
    -0.65
    ties
    -0.65
    baugh
    -0.64
    letters
    -0.63
    thia
    -0.62
    POSITIVE LOGITS
     glance
    1.17
     expense
    1.00
     disadvantage
    0.96
     behest
    0.94
     leisure
    0.93
     rate
    0.89
     whim
    0.89
     concess
    0.87
     checkpoint
    0.87
     whopping
    0.80
    Activations Density 0.065%

    No Known Activations