© 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. 20438
    Prev
    Next
    INDEX
    Explanations

    technical details about electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to retail units and device specifications

    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
    ictionary
    -0.78
    akespeare
    -0.76
    pmwiki
    -0.75
    anship
    -0.74
    ruciating
    -0.72
     atmosp
    -0.71
    itual
    -0.70
    ateurs
    -0.70
     Dickens
    -0.70
     clipboard
    -0.70
    POSITIVE LOGITS
     unveiling
    1.25
     unveiled
    1.19
     unveil
    1.18
     priced
    1.16
     Specifications
    1.15
     specs
    1.14
     specifications
    1.14
     Lenovo
    1.09
     pricing
    1.07
     teased
    1.07
    Activations Density 0.354%

    No Known Activations