© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1609
    Prev
    Next
    INDEX
    Explanations

    the last names of individuals or fictional characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Rog" and references to methodology in a scientific or analytical context

    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
     haze
    -0.76
     Harbor
    -0.75
    Offline
    -0.67
    Lake
    -0.65
    ange
    -0.65
     flask
    -0.65
     Woods
    -0.64
    weather
    -0.64
     cloud
    -0.63
    aila
    -0.63
    POSITIVE LOGITS
     Rog
    1.94
     Prim
    1.64
     methodology
    1.48
     Omn
    1.15
     Anim
    1.11
     Carn
    1.09
    Rog
    1.09
     Ci
    1.08
     Domin
    1.07
     methodological
    1.04
    Activations Density 0.053%

    No Known Activations