© 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 EvalsExportsinterp-engineNEWAPI 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. 11450
    Prev
    Next
    INDEX
    Explanations

    words related to current events or present situations

    oai_token-act-pair · gpt-3.5-turbo

    references to the present time

    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
     similarity
    -0.60
     Mata
    -0.58
     similarities
    -0.56
     Ammunition
    -0.55
    ortment
    -0.52
     Trouble
    -0.52
     pointers
    -0.52
     ZIP
    -0.52
     Tenth
    -0.51
     bounty
    -0.51
    POSITIVE LOGITS
    adays
    1.57
    here
    1.36
    abouts
    1.04
    heres
    1.02
     defunct
    0.87
    tics
    0.84
    terday
    0.83
    heric
    0.80
    orthy
    0.79
    lins
    0.72
    Activations Density 0.085%

    No Known Activations