© 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. 6-RES-JB
    11. 7865
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific observations and experiments

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific observations and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •test

    No Comments

    Negative Logits
    cit
    -0.84
    ikuman
    -0.79
    interstitial
    -0.75
    xit
    -0.74
    gur
    -0.72
    shr
    -0.69
    rax
    -0.67
    recy
    -0.67
     GDDR
    -0.67
    lins
    -0.66
    POSITIVE LOGITS
     observation
    1.03
     Observ
    0.92
     observing
    0.76
     observations
    0.75
     Procedures
    0.72
     patterns
    0.72
     observe
    0.71
    eering
    0.70
     observed
    0.70
     Telescope
    0.68
    Activations Density 0.033%

    No Known Activations