© 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. 3-RES-JB
    11. 23901
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or searching for something

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive occurrence of the substring "Se" in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.75
    etheless
    -0.72
    dayName
    -0.70
     diplom
    -0.70
     wire
    -0.70
    aneers
    -0.69
    sburgh
    -0.68
    Downloadha
    -0.68
     treating
    -0.67
     realism
    -0.66
    POSITIVE LOGITS
    eker
    1.16
    vere
    1.15
    venth
    1.14
    asons
    1.06
    quel
    1.03
    ldom
    1.00
    ju
    0.99
    ethe
    0.98
    lected
    0.96
    ems
    0.96
    Activations Density 0.012%

    No Known Activations