© 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 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. 10-RES-JB
    11. 4873
    Prev
    Next
    INDEX
    Explanations

    phrases related to possessions or specifications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quished
    -0.81
    izoph
    -0.74
    姫
    -0.72
    ivating
    -0.69
    cend
    -0.68
    uber
    -0.68
    uce
    -0.65
    izen
    -0.64
    MpServer
    -0.64
    oris
    -0.63
    POSITIVE LOGITS
    rather
    1.50
     rather
    1.49
     whereas
    1.38
     not
    1.28
     NOT
    1.10
    not
    1.05
     instead
    1.04
     namely
    1.04
     hence
    1.01
     albeit
    1.00
    Activations Density 0.401%

    No Known Activations