© 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. 0-RES-JB
    11. 11265
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical structures

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atz
    -0.68
    bat
    -0.65
    sung
    -0.64
    lethal
    -0.64
     Miss
    -0.64
     Medals
    -0.63
    bert
    -0.63
    deals
    -0.63
    hops
    -0.63
     Detective
    -0.62
    POSITIVE LOGITS
     structure
    3.64
     Structure
    2.85
     structures
    2.65
    ructure
    1.78
     stru
    1.71
     Struct
    1.70
     structured
    1.50
     structural
    1.44
     mechanism
    1.43
     struct
    1.39
    Activations Density 0.022%

    No Known Activations