© 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. 3329
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events or topics

    oai_token-act-pair · gpt-3.5-turbo

    the term "significant" and its variations in different 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
    ©¶æ
    -0.89
    iverpool
    -0.81
    av
    -0.76
    adobe
    -0.71
    vern
    -0.70
    eez
    -0.70
    nery
    -0.70
    called
    -0.68
    IDES
    -0.66
    bable
    -0.66
    POSITIVE LOGITS
     amounts
    1.22
     amount
    1.15
     quantities
    1.10
    itarian
    1.08
     differences
    1.07
     portions
    1.05
     improvement
    1.04
     reductions
    1.02
     understatement
    1.00
     quantity
    1.00
    Activations Density 0.076%

    No Known Activations