© 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. 6050
    Prev
    Next
    INDEX
    Explanations

    specific words and phrases related to technology and protocols

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly names of people and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Dynam
    -0.93
     Rosenberg
    -0.93
    åī
    -0.89
     Garg
    -0.82
     Univ
    -0.82
     Marshall
    -0.79
     Jav
    -0.79
     Ralph
    -0.78
     garg
    -0.78
     Finn
    -0.78
    POSITIVE LOGITS
    esse
    1.31
    asse
    1.24
    ne
    1.23
    ase
    1.20
    ce
    1.15
    te
    1.14
    ele
    1.13
    ze
    1.13
    CE
    1.13
    ene
    1.12
    Activations Density 0.264%

    No Known Activations