© 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. 9-RES-JB
    11. 16108
    Prev
    Next
    INDEX
    Explanations

    phrases related to having knowledge or experience in a particular field

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive use of the phrase "we have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imo
    -0.81
    weed
    -0.74
    âĺħ
    -0.68
    oshi
    -0.68
    eem
    -0.67
    attery
    -0.64
    TG
    -0.61
    inducing
    -0.61
    drive
    -0.61
    ogo
    -0.60
    POSITIVE LOGITS
     ourselves
    1.22
     been
    1.02
     seen
    1.01
     heard
    0.92
     witnessed
    0.88
     gotten
    0.86
     talked
    0.85
     our
    0.85
     begun
    0.84
     learned
    0.80
    Activations Density 0.139%

    No Known Activations