© 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. 11-RES-JB
    6. 17500
    Prev
    Next
    INDEX
    Explanations

    quantities or numbers of people or things

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantity or number of people involved in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESE
    -0.63
    schild
    -0.60
    artz
    -0.60
    illard
    -0.59
    Leaks
    -0.59
    ettel
    -0.59
     guiActiveUnfocused
    -0.58
    oug
    -0.57
    isu
    -0.57
    ask
    -0.57
    POSITIVE LOGITS
     others
    2.03
     other
    1.92
    other
    1.58
     Others
    1.45
     else
    1.44
     OTHER
    1.42
    Others
    1.33
     Other
    1.31
    OTHER
    1.25
    Other
    1.23
    Activations Density 0.265%

    No Known Activations