© 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. 0-RES-JB
    11. 13739
    Prev
    Next
    INDEX
    Explanations

    words related to suitability or correctness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "appropriate" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stru
    -0.72
    hunt
    -0.70
    ei
    -0.65
    illon
    -0.64
    tons
    -0.64
    axy
    -0.63
    ipe
    -0.62
     Travels
    -0.61
    eta
    -0.60
     broke
    -0.60
    POSITIVE LOGITS
     appropriate
    3.66
    appropriate
    2.55
     appropriately
    1.99
     suitable
    1.91
     relevant
    1.89
     proper
    1.86
     Appropri
    1.86
     applicable
    1.83
    appropriately
    1.74
     pertinent
    1.68
    Activations Density 0.015%

    No Known Activations