© 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. 1986
    Prev
    Next
    INDEX
    Explanations

    phrases related to decomposition and carcasses

    oai_token-act-pair · gpt-3.5-turbo

    terms related to decomposition and the remains of living organisms

    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
     privilege
    -0.66
     guard
    -0.62
     ridge
    -0.61
     Pell
    -0.60
     Graham
    -0.59
     buckle
    -0.58
     promise
    -0.58
    xon
    -0.57
     prov
    -0.56
     Kanye
    -0.55
    POSITIVE LOGITS
    posing
    1.21
    position
    1.08
    poses
    1.02
    pose
    0.98
    ission
    0.97
    aband
    0.94
    posal
    0.88
    nation
    0.85
    acements
    0.85
    pos
    0.84
    Activations Density 0.089%

    No Known Activations