INDEX

Explanations

references to verbal communication and language

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

verbal

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

 Maschine

-0.51

⎩

-0.49

 idolatry

-0.48

 aristocracy

-0.47

Insee

-0.47

 despotism

-0.46

 GridLayout

-0.46

бият

-0.46

Дизайн

-0.46

ipedia

-0.45

POSITIVE LOGITS

 verbal

2.03

Verbal

1.93

verbal

1.92

 Verbal

1.86

 verbally

1.74

 nonverbal

0.83

 vocal

0.76

Vocal

0.71

 Vocal

0.69

vocal

0.68

Activations Density 0.004%

references to verbal communication and language

verbal

No Comments

No Known Activations