INDEX

Explanations

questions and responses in a conversational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 endblock

-0.73

 numerus

-0.64

UpInside

-0.63

 AssemblyTitle

-0.61

 betweenstory

-0.60

')->

-0.60

存于互联网档案馆

-0.58

makeText

-0.57

Inflater

-0.55

Дереккөздер

-0.54

POSITIVE LOGITS

 sounds

1.35

Sounds

1.31

 Sounds

1.30

sounds

1.18

 klingt

0.83

 SOUND

0.80

Likely

0.79

 sounding

0.78

seamnă

0.77

 sonidos

0.76

Activations Density 0.302%

questions and responses in a conversational context

No Comments

No Known Activations