© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 18594
    Prev
    Next
    INDEX
    Explanations

    names of individuals related to sports and business

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals associated with a sports team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ington
    -0.95
    neys
    -0.90
    intosh
    -0.86
    nie
    -0.83
    borg
    -0.83
    ern
    -0.81
    ishers
    -0.81
    seys
    -0.81
    ney
    -0.79
    osphere
    -0.79
    POSITIVE LOGITS
     cane
    0.83
     thirst
    0.69
     conditioning
    0.69
     poppy
    0.68
     faint
    0.66
     distinguishing
    0.66
     bott
    0.65
     juice
    0.65
     bearer
    0.65
     stret
    0.65
    Activations Density 0.030%

    No Known Activations