© 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. 2-RES-JB
    11. 13606
    Prev
    Next
    INDEX
    Explanations

    phrases or acronyms containing "AM"

    oai_token-act-pair · gpt-3.5-turbo

    the specific time designations, particularly those related to the "AM" hours

    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
    ttes
    -0.84
     Norn
    -0.79
    ãĤ¬
    -0.74
    vous
    -0.73
    ãģį
    -0.71
    leans
    -0.67
    ãĥ¼ãĥ«
    -0.64
     Dys
    -0.62
     Schwar
    -0.62
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
    POSITIVE LOGITS
    sterdam
    1.16
    endment
    1.05
    AZ
    0.97
    AM
    0.93
    essage
    0.93
    PM
    0.92
    OUNT
    0.90
    endi
    0.84
    ICAN
    0.82
    azon
    0.82
    Activations Density 0.007%

    No Known Activations