© 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. 1-RES-JB
    11. 6721
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of the word "mum" with high activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "mum" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAW
    -0.70
    UCK
    -0.66
    RAFT
    -0.66
    kefeller
    -0.65
    III
    -0.64
    INGS
    -0.64
    rd
    -0.60
     Psychological
    -0.60
    PRES
    -0.59
    SELECT
    -0.59
    POSITIVE LOGITS
     mum
    1.22
    mers
    0.99
    ming
    0.85
    borgh
    0.83
     Mum
    0.81
    ples
    0.76
    wife
    0.73
     lapt
    0.72
    ma
    0.70
    mer
    0.70
    Activations Density 0.002%

    No Known Activations