© 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. 16071
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving an overwhelming amount of something

    oai_token-act-pair · gpt-3.5-turbo

    derivative forms of the verb "to guard" in various contexts

    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
    emb
    -0.84
    mington
    -0.68
    orig
    -0.64
     Fei
    -0.61
     Frazier
    -0.60
    embed
    -0.60
    adra
    -0.59
    psons
    -0.59
    icago
    -0.58
     rapp
    -0.58
    POSITIVE LOGITS
    arding
    1.27
    arded
    1.16
    ertodd
    0.95
    ards
    0.91
    ARDS
    0.79
    mallow
    0.78
    ard
    0.78
    ritic
    0.78
    abies
    0.71
    ynamic
    0.71
    Activations Density 0.006%

    No Known Activations