© 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. 10-RES-JB
    6. 12436
    Prev
    Next
    INDEX
    Explanations

    phrases related to impressive or awe-inspiring elements

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names related to movies and fictional concepts

    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
     Boyle
    -0.90
     Carib
    -0.84
     Cot
    -0.82
    692
    -0.79
    cycles
    -0.76
     Cantor
    -0.76
     ropes
    -0.76
     rag
    -0.72
    OTS
    -0.71
     Bohem
    -0.70
    POSITIVE LOGITS
    en
    1.67
    EN
    1.64
    ens
    1.32
    ename
    1.25
    enf
    1.20
    ena
    1.18
    ensen
    1.18
    én
    1.17
     EN
    1.16
    eni
    1.16
    Activations Density 0.186%

    No Known Activations