© 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. 9-RES-JB
    11. 13348
    Prev
    Next
    INDEX
    Explanations

    words related to abstract concepts like symbolism or political movements

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to descriptive adjectives and adverbs

    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
     Instruments
    -0.67
    é¾įå
    -0.67
     Tuc
    -0.65
     Clan
    -0.64
     Nou
    -0.61
     gad
    -0.61
     Ou
    -0.60
     Izan
    -0.60
     TAMADRA
    -0.60
     Congo
    -0.60
    POSITIVE LOGITS
    rics
    1.09
    phal
    0.92
    te
    0.90
    ctors
    0.88
    rical
    0.87
    iology
    0.87
    tes
    0.85
    isma
    0.84
    rand
    0.84
    ption
    0.84
    Activations Density 0.209%

    No Known Activations