© 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. 16934
    Prev
    Next
    INDEX
    Explanations

    names of individuals, potentially famous or involved in conflicts

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals

    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
    accompan
    -0.66
     incess
    -0.65
    internet
    -0.61
    etter
    -0.60
    bones
    -0.60
     Opposition
    -0.59
    warts
    -0.58
    conserv
    -0.58
    ãģ®éŃĶ
    -0.58
    NRS
    -0.58
    POSITIVE LOGITS
    abeth
    0.81
    ipel
    0.73
    ema
    0.72
     Tasman
    0.72
    ÄŁ
    0.69
    ENE
    0.68
     Cummings
    0.67
     Choi
    0.66
    vironment
    0.66
    onomic
    0.65
    Activations Density 0.210%

    No Known Activations