© 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. 13527
    Prev
    Next
    INDEX
    Explanations

    phrases related to public availability or access

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference accessibility to the general public

    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
    illac
    -0.96
    sterdam
    -0.70
    dylib
    -0.68
    ibal
    -0.66
    NetMessage
    -0.66
    iHUD
    -0.65
    gars
    -0.62
    nam
    -0.62
    tackle
    -0.60
    irection
    -0.59
    POSITIVE LOGITS
     public
    1.39
     masses
    1.36
     populace
    1.30
     wider
    1.18
     audience
    1.17
     world
    1.14
     electorate
    1.10
     reader
    1.08
     rest
    1.06
     viewers
    1.05
    Activations Density 0.257%

    No Known Activations