© 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. 7100
    Prev
    Next
    INDEX
    Explanations

    texts discussing technical information related to data analysis, programming, and technology

    oai_token-act-pair · gpt-3.5-turbo

    frequent or key terms related to data analysis and technical processes

    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
     neighb
    -0.82
     enriched
    -0.81
     claws
    -0.77
     sermon
    -0.76
     jailed
    -0.76
     migr
    -0.74
     landsl
    -0.74
     aromatic
    -0.73
     accomp
    -0.73
     occupation
    -0.73
    POSITIVE LOGITS
    Sometimes
    1.75
    Whenever
    1.73
    When
    1.72
    There
    1.69
    Before
    1.68
    While
    1.66
    Whether
    1.66
    Every
    1.66
    If
    1.65
    Although
    1.64
    Activations Density 0.147%

    No Known Activations