INDEX

Explanations

phrases that indicate effort, time spent, or complexity in tasks

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.67

urlpatterns

-0.60

 }}"></

-0.56

 متعلقه

-0.54

providedIn

-0.52

 propOrder

-0.52

 pełni

-0.52

InjectAttribute

-0.52

最快更新

-0.52

MENAFN

-0.51

POSITIVE LOGITS

 planning

0.76

 research

0.70

 detective

0.70

 thought

0.70

leg

0.70

 searching

0.68

 prep

0.67

 thinking

0.66

 tweaking

0.64

 fidd

0.63

Activations Density 0.304%

phrases that indicate effort, time spent, or complexity in tasks

No Comments

No Known Activations