Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 18547
    Prev
    Next
    INDEX
    Explanations

    countries and names starting with the letter "S."

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.71
    addle
    -0.67
    xual
    -0.63
    razen
    -0.60
    culosis
    -0.58
    ikuman
    -0.55
    eport
    -0.55
     è£ıè
    -0.54
    oola
    -0.54
     pockets
    -0.52
    POSITIVE LOGITS
     Malf
    0.63
     Maced
    0.63
     Trails
    0.53
     Monteneg
    0.53
     Monaco
    0.52
     Monstrous
    0.52
    Ħ¢
    0.51
    taboola
    0.51
    tti
    0.49
     decaying
    0.49
    Activations Density 1.029%

    No Known Activations