© 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. 10-RES-JB
    11. 2949
    Prev
    Next
    INDEX
    Explanations

    phrases related to superiority or excellence

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases related to the state of something, particularly in a professional or artistic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bakr
    -0.75
     groom
    -0.75
     chant
    -0.71
     Seah
    -0.69
     Doodle
    -0.69
     Ivanka
    -0.68
     plunge
    -0.68
     Britann
    -0.68
     Rohingya
    -0.68
    ħĭ
    -0.68
    POSITIVE LOGITS
    the
    1.38
    your
    1.37
    speech
    1.36
    origin
    1.34
    advertising
    1.33
    nature
    1.31
    sight
    1.31
    interest
    1.30
    life
    1.29
    purpose
    1.29
    Activations Density 0.038%

    No Known Activations