© 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. 7-RES-JB
    11. 20631
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "That is how" followed by a strong opinion or personal perspective

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate explanations or descriptions of processes

    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
    Quest
    -0.63
    room
    -0.62
    effects
    -0.60
    artifacts
    -0.60
    wear
    -0.57
     hereafter
    -0.57
     yak
    -0.57
    actor
    -0.57
    iston
    -0.56
    oris
    -0.56
    POSITIVE LOGITS
    beit
    0.71
    ativity
    0.69
    pedia
    0.69
    HCR
    0.68
    erest
    0.67
    soever
    0.66
    bill
    0.64
    ls
    0.62
    pher
    0.61
     much
    0.61
    Activations Density 0.030%

    No Known Activations