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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3172
    Prev
    Next
    INDEX
    Explanations

    comparatively strong entities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of strength or being stronger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rolley
    -0.87
    pty
    -0.84
    ourn
    -0.68
     Newly
    -0.68
    mits
    -0.68
    mberg
    -0.68
    adr
    -0.67
     Lyons
    -0.66
     Roche
    -0.66
    ffe
    -0.66
    POSITIVE LOGITS
     streng
    1.08
     referen
    1.02
     veter
    0.98
     stronger
    0.97
     advoc
    0.94
     strength
    0.94
     weaker
    0.91
     tremend
    0.90
     undermin
    0.89
     behavi
    0.88
    Activations Density 0.008%

    No Known Activations