INDEX

Explanations

occurrences of the word "contain" and its variations

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

contains

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

 ſta

-0.68

ſelf

-0.57

AnimationsModule

-0.56

 ſte

-0.55

 fubject

-0.52

 Anſ

-0.49

 ſur

-0.49

 ſche

-0.48

 faſt

-0.48

 ſou

-0.47

POSITIVE LOGITS

 contains

0.98

 contain

0.97

contain

0.95

 Contain

0.93

Contain

0.91

Contains

0.90

 Contains

0.88

contains

0.83

 containing

0.82

 Containing

0.74

Activations Density 0.038%

occurrences of the word "contain" and its variations

contains

No Comments

No Known Activations