© 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. 17460
    Prev
    Next
    INDEX
    Explanations

    phrases related to frequency or repetition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or recurrence of events

    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
    ocate
    -0.72
    ̶
    -0.68
    oulos
    -0.66
    oola
    -0.66
    robe
    -0.66
    GGGGGGGG
    -0.65
    apolis
    -0.64
    lance
    -0.64
    argon
    -0.63
     Presence
    -0.63
    POSITIVE LOGITS
     occasions
    1.89
     occasion
    1.70
     fronts
    1.39
     basis
    1.34
     behalf
    1.27
     pretext
    1.18
     continents
    1.17
     grounds
    1.12
     occ
    1.05
     campuses
    1.02
    Activations Density 0.126%

    No Known Activations