© 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. 23577
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames prefixed with the @ symbol

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media handles or tags

    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
     aspir
    -0.71
     immersion
    -0.70
     stricken
    -0.68
     orche
    -0.68
     elect
    -0.68
     exorc
    -0.66
     shack
    -0.66
     Takeru
    -0.65
     royalty
    -0.65
     retali
    -0.64
    POSITIVE LOGITS
    username
    0.93
    #$
    0.89
     (@
    0.85
    deck
    0.85
    tip
    0.81
    hello
    0.81
    usage
    0.79
    self
    0.79
    ANI
    0.78
    maximum
    0.77
    Activations Density 0.013%

    No Known Activations