INDEX

Explanations

references to time, particularly the word "last" and various forms of "season" or "year."

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

last or previous time period

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

تقاوى

-0.45

 kaarangay

-0.38

poons

-0.37

 protoimpl

-0.36

RenderAtEndOf

-0.35

CardHeader

-0.35

 rotund

-0.35

postsleuth

-0.35

urlpatterns

-0.34

POSITIVE LOGITS

 vorige

0.98

 förra

0.96

 scorso

0.79

 vorigen

0.79

 précédente

0.79

 poprzed

0.76

 précédents

0.75

Previous

0.74

 предыду

0.73

前回の

0.73

Activations Density 0.056%

references to time, particularly the word "last" and various forms of "season" or "year."

last or previous time period

No Comments

No Known Activations

references to time, particularly the word "last" and various forms of "season" or "year."

last or previous time period

No Comments

No Known Activations