© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 15822
    Prev
    Next
    INDEX
    Explanations

    comparative words or phrases indicating a higher level or degree

    oai_token-act-pair · gpt-3.5-turbo

    the word "even" and its contextual emphasis on comparative or superlative qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneers
    -0.77
    ĺħ
    -0.71
    ULTS
    -0.68
     Challenges
    -0.66
     Rica
    -0.65
    ATURES
    -0.65
     Scenes
    -0.65
    Ú
    -0.65
     Bridges
    -0.65
     Elaine
    -0.64
    POSITIVE LOGITS
    usal
    0.70
     derivative
    0.70
     variant
    0.68
     lineup
    0.67
     opener
    0.65
    vil
    0.65
     cape
    0.64
     formula
    0.64
     genus
    0.63
    ogram
    0.63
    Activations Density 1.172%

    No Known Activations