© 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. 12-RES-JB
    11. 3873
    Prev
    Next
    INDEX
    Explanations

    numerical values preceded by the letter 'v'

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

    words that are related to levels or measurements

    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
     Mafia
    -0.67
     lod
    -0.65
     Border
    -0.64
     Luxembourg
    -0.63
     Maver
    -0.63
     Moon
    -0.62
     Passenger
    -0.59
     Lob
    -0.58
     Sheep
    -0.58
     Factory
    -0.58
    POSITIVE LOGITS
    olution
    1.44
    ocation
    1.27
    ailing
    1.24
    ocations
    1.22
    iew
    1.22
    ices
    1.21
    olved
    1.21
    idences
    1.20
    ocative
    1.18
    incial
    1.18
    Activations Density 0.052%

    No Known Activations