© 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. 2252
    Prev
    Next
    INDEX
    Explanations

    appearing patterns related to names and titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character 'O' with various diacritical marks

    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
     screen
    -0.62
     microphones
    -0.60
     fulfillment
    -0.60
     synd
    -0.59
     screens
    -0.58
     JC
    -0.58
     snacks
    -0.57
     sadly
    -0.57
     DNA
    -0.56
     Nightmares
    -0.56
    POSITIVE LOGITS
    ĸļ
    1.51
    ¡
    1.46
    ¬
    1.43
    ħ
    1.39
    ı
    1.39
    Ĵ
    1.38
    °
    1.32
    Ķ
    1.31
    ĸ
    1.31
    ĵ
    1.30
    Activations Density 0.072%

    No Known Activations