INDEX

Explanations

references to location or context within a narrative

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

basicConfig

-0.56

代わりに

-0.53

ynchronously

-0.53

 optionally

-0.53

ngdoc

-0.52

 instead

-0.51

CrossRef

-0.50

rizona

-0.49

 ImGui

-0.49

 TextAppearance

-0.49

POSITIVE LOGITS

 terms

2.28

terms

1.72

 termes

1.46

Terms

1.41

 TERMS

1.38

 termos

1.38

 Terms

1.35

 regards

1.32

 términos

1.28

 regard

1.24

Activations Density 0.460%

references to location or context within a narrative

No Comments

No Known Activations