© 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. 0-RES-JB
    11. 15593
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Hausenf" or "Hausen" at various activations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, particularly with the root "aus."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jarrett
    -0.73
     keyword
    -0.70
     controller
    -0.64
     shader
    -0.63
     Moody
    -0.61
     controllers
    -0.61
     Controller
    -0.60
     rap
    -0.59
     silenced
    -0.59
     promoter
    -0.59
    POSITIVE LOGITS
    aus
    4.86
    au
    1.42
    ausible
    1.30
    aos
    1.25
    AU
    1.21
    aux
    1.14
    anus
    1.14
    aud
    1.11
    haus
    1.07
    ause
    1.05
    Activations Density 0.013%

    No Known Activations