© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3228
    Prev
    Next
    INDEX
    Explanations

    words related to influencing change or having an impact on various aspects of life

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the concept of "how" something is done or perceived

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gur
    -0.79
    gin
    -0.74
    qv
    -0.72
    ãĤ¤ãĥĪ
    -0.67
    yang
    -0.66
    duty
    -0.65
    IFIED
    -0.65
    claim
    -0.65
    quist
    -0.64
    unity
    -0.64
    POSITIVE LOGITS
    soever
    1.13
     humans
    0.94
     individuals
    0.93
     people
    0.92
     much
    0.91
     we
    0.89
     societies
    0.85
     they
    0.85
     efficiently
    0.83
    ls
    0.83
    Activations Density 0.080%

    No Known Activations