© 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. 2-RES-JB
    11. 944
    Prev
    Next
    INDEX
    Explanations

    the word "Together" when it is capitalized and used at the beginning of a sentence or phrase

    oai_token-act-pair · gpt-4-turbo

    phrases related to collaboration or unity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Together."

    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
    ouses
    -0.77
     congestion
    -0.72
    ascus
    -0.71
     livest
    -0.70
     denial
    -0.68
     visitation
    -0.66
     latch
    -0.65
    rection
    -0.64
     plague
    -0.63
     mystery
    -0.63
    POSITIVE LOGITS
     Together
    1.12
    Together
    0.94
    halla
    0.83
    SourceFile
    0.80
    mates
    0.80
     Packs
    0.79
     Colors
    0.74
     Alone
    0.73
     Plug
    0.73
     Include
    0.73
    Activations Density 0.014%

    No Known Activations