INDEX

Explanations

references to voice and vocal expressions, particularly in the context of technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glers

-0.80

 Mercier

-0.72

Tembelea

-0.70

simi

-0.69

 Dekker

-0.67

txn

-0.65

 monasteries

-0.65

edicated

-0.65

weds

-0.65

OGND

-0.65

POSITIVE LOGITS

 voice

1.83

 Voice

1.66

 voices

1.57

 VOICE

1.57

 Voices

1.55

voice

1.55

Voice

1.54

VOICE

1.43

voices

1.42

Voices

1.39

Activations Density 0.058%

references to voice and vocal expressions, particularly in the context of technology

No Comments

No Known Activations