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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2-RES-JB
    6. 518
    Prev
    Next
    INDEX
    Explanations

    the brand name "Flipkart"

    oai_token-act-pair · gpt-4-turbo

    mentions of the company "Flipkart" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Flip" and related aspects of its business

    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
    rawdownloadcloneembedreportprint
    -0.75
    ä¹ĭ
    -0.74
    é¾
    -0.73
    ä¸Ń
    -0.69
    >>>>>>>>
    -0.67
    Ñı
    -0.67
    UGH
    -0.67
    ULT
    -0.67
    RAFT
    -0.66
    íķ
    -0.66
    POSITIVE LOGITS
     Flip
    1.06
    oslav
    0.83
    tsy
    0.82
    endra
    0.80
    opt
    0.79
    ibaba
    0.79
    orius
    0.77
    visor
    0.76
    assi
    0.76
    fix
    0.74
    Activations Density 0.013%

    No Known Activations