© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12830
    Prev
    Next
    INDEX
    Explanations

    references to the World Cup event

    oai_token-act-pair · gpt-3.5-turbo

    references to the World Cup

    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
    imaru
    -0.78
    */(
    -0.76
    yout
    -0.74
    eton
    -0.72
    terday
    -0.72
    ogyn
    -0.72
    shown
    -0.72
     Anon
    -0.71
    ipt
    -0.70
    bart
    -0.70
    POSITIVE LOGITS
     qualifier
    1.21
     Finals
    1.21
     Playoffs
    1.20
     qualifiers
    1.20
     Qual
    1.15
     finals
    1.13
     qualifying
    1.11
     qualification
    0.99
     semifinals
    0.98
     Final
    0.98
    Activations Density 0.057%

    No Known Activations