© 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. 7-RES-JB
    11. 3029
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense that happened recently

    oai_token-act-pair · gpt-3.5-turbo

    present tense and past tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LV
    -0.68
     centr
    -0.65
     concedes
    -0.61
     theoret
    -0.61
     Cald
    -0.59
     Hawai
    -0.59
     Providence
    -0.58
    ão
    -0.58
    ®
    -0.58
     DNC
    -0.58
    POSITIVE LOGITS
    senal
    1.25
    ĸļ
    1.04
    Ĥİ
    0.86
    ļéĨĴ
    0.85
    é¾į
    0.82
    £ı
    0.81
    ADRA
    0.78
    uten
    0.76
     indistinguishable
    0.75
    è£ħ
    0.74
    Activations Density 0.432%

    No Known Activations