© 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. 0-RES-JB
    11. 14814
    Prev
    Next
    INDEX
    Explanations

    past tense verbs ending in 'ed' or related to actions being carried out

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "turned."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Commerce
    -0.64
    regate
    -0.63
    omsday
    -0.62
    ford
    -0.59
    pez
    -0.58
     existing
    -0.56
    zza
    -0.55
     Articles
    -0.55
    erous
    -0.55
    landers
    -0.54
    POSITIVE LOGITS
     turned
    3.25
    turned
    2.25
     turns
    1.97
     turn
    1.87
     Turn
    1.54
    Turn
    1.51
     Turns
    1.49
     morphed
    1.48
     switched
    1.46
    turn
    1.46
    Activations Density 0.021%

    No Known Activations