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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 7460
    Prev
    Next
    INDEX
    Explanations

    the word "lo" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Loco" or variations related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICLE
    -0.72
     signature
    -0.70
    ãĥĩ
    -0.70
     conventions
    -0.68
    rations
    -0.67
     Convention
    -0.66
    sonian
    -0.63
    ãĥĺãĥ©
    -0.63
     electron
    -0.62
    é¾
    -0.62
    POSITIVE LOGITS
    fty
    1.05
    opy
    1.00
    zzle
    0.99
    pper
    0.99
    zzi
    0.97
    oping
    0.97
    ppy
    0.95
    efe
    0.92
    opes
    0.91
    zz
    0.89
    Activations Density 0.008%

    No Known Activations