© 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. 20503
    Prev
    Next
    INDEX
    Explanations

    phrases related to imitations or replicas

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "knock" 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
    stice
    -0.83
    emale
    -0.77
    heny
    -0.72
     DISTRICT
    -0.67
    ivities
    -0.65
    ceed
    -0.64
    ional
    -0.64
    mberg
    -0.64
    xia
    -0.63
    heid
    -0.63
    POSITIVE LOGITS
    down
    1.13
     down
    0.92
    about
    0.90
     knock
    0.89
    downs
    0.86
     unconscious
    0.84
    kn
    0.83
     senseless
    0.80
    offs
    0.76
    boxing
    0.75
    Activations Density 0.036%

    No Known Activations