© 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. 11-RES-JB
    11. 20623
    Prev
    Next
    INDEX
    Explanations

    scientific terms and keywords related to research studies and investigations

    oai_token-act-pair · gpt-3.5-turbo

    academic research terminology and analysis

    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
    SPONSORED
    -0.84
    isSpecialOrderable
    -0.82
    ittee
    -0.78
    reet
    -0.73
    dt
    -0.73
    iva
    -0.72
    lists
    -0.71
    ifa
    -0.70
    lite
    -0.67
    onest
    -0.67
    POSITIVE LOGITS
     effects
    1.34
     origins
    1.30
     dynamics
    1.28
     relationship
    1.28
     workings
    1.28
     role
    1.27
     impact
    1.21
     impacts
    1.20
     evolution
    1.17
     effectiveness
    1.14
    Activations Density 0.212%

    No Known Activations