© 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. 3-RES-JB
    11. 6303
    Prev
    Next
    INDEX
    Explanations

    the word "curve" preceded by an adjective or phrase in the COVID-19 dataset

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of curves, particularly in a statistical or metaphorical context

    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
    alty
    -0.76
    ynski
    -0.68
    @#&
    -0.66
     Duty
    -0.66
    oral
    -0.65
     Said
    -0.63
     Ans
    -0.63
     Universal
    -0.63
    akings
    -0.62
    aples
    -0.62
    POSITIVE LOGITS
    balls
    1.14
     curve
    1.11
     curves
    1.05
     Curve
    1.01
    atism
    0.90
    ball
    0.86
     curv
    0.85
     flatt
    0.81
     slope
    0.81
     shif
    0.80
    Activations Density 0.011%

    No Known Activations