© 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. 2-RES-JB
    11. 6065
    Prev
    Next
    INDEX
    Explanations

    phrases indicating unnecessary excess or redundancy

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate redundancy or unnecessary information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arter
    -0.71
    lain
    -0.69
     mined
    -0.63
    roid
    -0.62
    ds
    -0.62
    abbling
    -0.61
    multi
    -0.61
     ank
    -0.60
    ammed
    -0.59
     Branch
    -0.59
    POSITIVE LOGITS
    mares
    0.86
    uits
    0.83
    uitous
    0.82
    iously
    0.81
    omore
    0.81
    ortun
    0.79
    atility
    0.79
    ĸļ
    0.77
    itial
    0.77
    Shape
    0.75
    Activations Density 0.013%

    No Known Activations