© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 2845
    Prev
    Next
    INDEX
    Explanations

    sentences indicating a similar situation, fact, or statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express equivalence or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.68
    ++++++++++++++++
    -0.59
    ded
    -0.54
    vironment
    -0.54
    Str
    -0.53
    itory
    -0.52
     distraction
    -0.50
    zos
    -0.50
     Slim
    -0.50
     Bones
    -0.50
    POSITIVE LOGITS
     applies
    1.06
     apply
    0.99
     applied
    0.86
     applicable
    0.74
     prev
    0.73
     happ
    0.73
    Applic
    0.69
    aila
    0.68
     prevailed
    0.68
    iat
    0.68
    Activations Density 0.201%

    No Known Activations