© 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. 7-RES-JB
    11. 13713
    Prev
    Next
    INDEX
    Explanations

    keywords related to locations and constructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and the prepositions related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iffe
    -0.79
     besides
    -0.76
    SPONSORED
    -0.71
     without
    -0.68
    iety
    -0.68
     justifies
    -0.67
     compares
    -0.66
    ature
    -0.65
    thood
    -0.64
    pport
    -0.64
    POSITIVE LOGITS
     same
    1.17
     assumption
    1.07
     highest
    1.02
     aforementioned
    1.02
     smallest
    0.99
     lowest
    0.96
     latter
    0.95
     widest
    0.93
     premise
    0.93
     utmost
    0.90
    Activations Density 0.419%

    No Known Activations