© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3426
    Prev
    Next
    INDEX
    Explanations

    phrases related to weapon and conflict

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to phase" or related verb forms in various grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NG
    -0.74
    é¾įå
    -0.67
     Acad
    -0.66
    AMS
    -0.62
    Nev
    -0.62
    è¦ļéĨĴ
    -0.61
    WN
    -0.60
     âĢİ
    -0.60
    papers
    -0.60
    Greek
    -0.59
    POSITIVE LOGITS
    asing
    1.11
    xual
    1.03
    ased
    0.93
    chwitz
    0.92
    ases
    0.89
    asant
    0.81
    imar
    0.80
     Parenthood
    0.80
    iple
    0.79
    aser
    0.77
    Activations Density 0.010%

    No Known Activations