© 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. 2-RES-JB
    11. 6902
    Prev
    Next
    INDEX
    Explanations

    terms related to something being notable or significant

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words related to utility or usefulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aptic
    -0.88
    romy
    -0.82
    opsis
    -0.81
    raped
    -0.80
    href
    -0.76
    hetamine
    -0.74
    é¾įå
    -0.73
    adra
    -0.73
     Wond
    -0.71
    trak
    -0.71
    POSITIVE LOGITS
    itable
    1.09
     hazard
    0.74
    itably
    0.72
     reuse
    0.67
     adjustment
    0.67
     mixture
    0.66
     infinity
    0.65
     proportions
    0.65
     Immunity
    0.65
     convergence
    0.62
    Activations Density 0.010%

    No Known Activations