© 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. 13947
    Prev
    Next
    INDEX
    Explanations

    references to a specific sports team named "Jays"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Toronto Blue Jays

    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
    ãĤ·ãĥ£
    -0.80
    ALLY
    -0.76
    ãĥ´ãĤ¡
    -0.74
    Labor
    -0.71
    åij
    -0.68
    Las
    -0.66
    ãĥŁ
    -0.66
    isation
    -0.66
    natureconservancy
    -0.65
    inea
    -0.65
    POSITIVE LOGITS
     Jays
    1.14
    onet
    0.82
    haw
    0.81
    hap
    0.78
    ucc
    0.77
     outfielder
    0.74
     fortun
    0.73
     mosqu
    0.73
    ón
    0.71
    hao
    0.70
    Activations Density 0.006%

    No Known Activations