© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 21695
    Prev
    Next
    INDEX
    Explanations

    terms related to machine learning and artificial intelligence techniques

    oai_token-act-pair · gpt-3.5-turbo

    terms related to machine learning and artificial intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĤ
    -0.75
     unmarried
    -0.70
    union
    -0.69
    ãĤĮ
    -0.69
    uti
    -0.68
    illard
    -0.68
     unfinished
    -0.67
    uki
    -0.67
    illet
    -0.66
    çĦ
    -0.66
    POSITIVE LOGITS
     algorithms
    1.27
     algorithm
    1.05
    eers
    1.00
     systems
    0.92
     analy
    0.90
     apparatus
    0.86
     simulation
    0.86
     interfaces
    0.85
     technologies
    0.85
     analytics
    0.85
    Activations Density 0.322%

    No Known Activations