© 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. 1907
    Prev
    Next
    INDEX
    Explanations

    words related to difficulties or challenges

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "struggle" and its variations

    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
    ilipp
    -0.72
    gone
    -0.71
    ahu
    -0.71
    chnology
    -0.64
    asus
    -0.64
    resa
    -0.62
    othy
    -0.62
    DragonMagazine
    -0.62
    atures
    -0.60
    aurus
    -0.60
    POSITIVE LOGITS
     financially
    1.09
     valiant
    0.95
     withd
    0.94
     miser
    0.94
     immensely
    0.90
     economically
    0.89
     against
    0.86
     academ
    0.85
     with
    0.84
     unsuccessfully
    0.83
    Activations Density 0.060%

    No Known Activations