© 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. 6-RES-JB
    6. 11783
    Prev
    Next
    INDEX
    Explanations

    phrases related to something being well-known or famous for a certain quality or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something is well-known for its qualities or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brainer
    -0.72
    hm
    -0.65
     disg
    -0.63
    register
    -0.62
     PLEASE
    -0.62
    ova
    -0.61
    vier
    -0.61
    LET
    -0.60
     unconscious
    -0.60
    wake
    -0.60
    POSITIVE LOGITS
     unorthodox
    0.83
    ãĥīãĥ©
    0.73
     advoc
    0.72
     outspoken
    0.71
     musical
    0.71
     nickname
    0.70
     abras
    0.70
    negie
    0.70
     quirky
    0.67
     flashy
    0.67
    Activations Density 0.382%

    No Known Activations