© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4773
    Prev
    Next
    INDEX
    Explanations

    information related to specific events or announcements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words and phrases related to public access or availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    -0.90
    spell
    -0.68
    sterdam
    -0.66
    gars
    -0.65
    alach
    -0.63
    dylib
    -0.63
    ular
    -0.63
    brainer
    -0.63
    nam
    -0.60
    blem
    -0.58
    POSITIVE LOGITS
     public
    1.45
     masses
    1.24
     populace
    1.17
     general
    1.08
     world
    1.04
     electorate
    1.02
    public
    1.02
     wider
    1.01
     PUBLIC
    1.00
     widest
    0.97
    Activations Density 0.359%

    No Known Activations