© 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. 1-RES-JB
    11. 7166
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a conclusion or result

    oai_token-act-pair · gpt-3.5-turbo

    the word "Therefore" and its usage in various contexts

    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
    uc
    -0.62
     Carth
    -0.62
    ten
    -0.59
     DeL
    -0.59
    brand
    -0.57
     AAA
    -0.56
    ARC
    -0.56
     Mé
    -0.56
     Feld
    -0.56
     Comm
    -0.55
    POSITIVE LOGITS
    anwhile
    0.92
    etheless
    0.84
     dilig
    0.84
    Therefore
    0.84
     ende
    0.83
    rehend
    0.82
     compr
    0.82
    entimes
    0.82
     therefore
    0.81
     conclud
    0.80
    Activations Density 0.004%

    No Known Activations