© 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. 3-RES-JB
    6. 21277
    Prev
    Next
    INDEX
    Explanations

    references to the news network RT in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific news outlet, RT

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iasis
    -0.85
    ãĥ¼ãĥĨ
    -0.73
     Rockefeller
    -0.69
     Edison
    -0.64
     Samoa
    -0.64
    âĸĪâĸĪ
    -0.63
     pregnant
    -0.63
    ãĤ»
    -0.62
    ocene
    -0.62
    urities
    -0.62
    POSITIVE LOGITS
    Ãī
    1.17
    TY
    0.96
    TE
    0.90
    BF
    0.87
    casters
    0.86
    caster
    0.86
     RT
    0.83
    irtual
    0.82
    books
    0.78
    AKING
    0.77
    Activations Density 0.009%

    No Known Activations