© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 10187
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consolidation or combination of multiple elements into one unit

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to combining or integrating multiple elements into a single unit

    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
    lihood
    -0.75
    oris
    -0.75
    ffect
    -0.70
    oi
    -0.67
    ------------------------
    -0.67
    vale
    -0.66
    ror
    -0.66
    owners
    -0.66
    erk
    -0.65
    ãĥĥãĤ¯
    -0.65
    POSITIVE LOGITS
     manageable
    1.05
     coherent
    1.02
     neatly
    1.00
     tidy
    0.99
     single
    0.94
     cohesive
    0.93
     neat
    0.93
     nutshell
    0.89
     succinct
    0.83
     seamless
    0.82
    Activations Density 0.296%

    No Known Activations