© 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. 1-RES-JB
    11. 14045
    Prev
    Next
    INDEX
    Explanations

    the word "consistently" followed by other words

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "consistently."

    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
    tein
    -0.93
    irst
    -0.76
    atorium
    -0.70
    soc
    -0.69
    ogens
    -0.69
    OTOS
    -0.68
    ster
    -0.68
     Julius
    -0.66
    hak
    -0.66
    iao
    -0.65
    POSITIVE LOGITS
     consistently
    0.94
     conduc
    0.94
     strugg
    0.86
     conclud
    0.84
    uously
    0.81
     behaved
    0.80
    ciating
    0.80
     outper
    0.79
     inconsistent
    0.79
     msec
    0.79
    Activations Density 0.007%

    No Known Activations