© 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. 11-RES-JB
    11. 21107
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone is described as the sole or exclusive example of a certain category or condition

    oai_token-act-pair · gpt-3.5-turbo

    references to uniqueness or singularity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gradient
    -0.66
     [|
    -0.63
    utenberg
    -0.63
    deals
    -0.62
     Cosponsors
    -0.62
    èĪ
    -0.61
    tnc
    -0.61
    haul
    -0.60
    ahime
    -0.58
     whirlwind
    -0.57
    POSITIVE LOGITS
     remaining
    1.20
     capable
    1.00
     remotely
    0.97
     extant
    0.97
     sane
    0.96
     conceivable
    0.94
     truly
    0.94
     ever
    0.94
     besides
    0.92
     imaginable
    0.92
    Activations Density 0.246%

    No Known Activations