INDEX

Explanations

elements related to monotone or robotic speech patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ParallelGroup

-0.63

setGeometry

-0.61

 beginnetje

-0.59

 denk

-0.53

اریخ

-0.52

ómicos

-0.52

vertissement

-0.52

 utafitiHapana

-0.51

 calculées

-0.51

indd

-0.51

POSITIVE LOGITS

 voice

2.01

 voices

1.62

voice

1.61

 voix

1.47

 Voice

1.46

voz

1.42

Voice

1.42

 tone

1.39

 VOICE

1.38

voices

1.25

Activations Density 0.172%

elements related to monotone or robotic speech patterns

No Comments

No Known Activations