INDEX

Explanations

occurrences of the word "seen" and its variations

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

seeing or hearing

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

 autorytatywna

-0.44

 translateY

-0.42

TemporalType

-0.41

 pymysql

-0.41

NOTIFY

-0.41

 samarbeid

-0.40

 Californie

-0.39

 emplois

-0.39

izarse

-0.39

 functie

-0.39

POSITIVE LOGITS

 seen

0.92

seen

0.84

Seen

0.83

 Seen

0.76

 SEEN

0.67

见过

0.66

看过

0.62

saw

0.59

 been

0.59

 witnessed

0.57

Activations Density 0.012%

occurrences of the word "seen" and its variations

seeing or hearing

No Comments

No Known Activations