© 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
    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. 5748
    Prev
    Next
    INDEX
    Explanations

    phrases related to caravans

    oai_token-act-pair · gpt-3.5-turbo

    references to specific surnames

    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
     mathemat
    -0.81
     conduc
    -0.78
     prevailing
    -0.76
     reluct
    -0.76
     predictive
    -0.75
     ubiquitous
    -0.74
     corros
    -0.73
     relational
    -0.72
     pervasive
    -0.72
     fateful
    -0.72
    POSITIVE LOGITS
    avan
    1.31
    agh
    1.28
    ese
    0.88
    icz
    0.88
    athan
    0.85
    abal
    0.85
    ny
    0.83
    aughs
    0.83
    ica
    0.81
    ãĥ¥
    0.81
    Activations Density 0.007%

    No Known Activations