INDEX

Explanations

information on reading levels of books, specifically grade levels

oai_token-act-pair · gemini-2.0-flash

references to educational levels or grades

np_token-act-pair-logits · gpt-4o-mini

grade

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 eighth

-0.94

 seventh

-0.90

 ninth

-0.86

Seventh

-0.84

 Eighth

-0.77

 Seventh

-0.74

seventh

-0.73

 sixth

-0.71

th

-0.70

Sixth

-0.69

POSITIVE LOGITS

szönöm

0.73

 EconPapers

0.60

 mẽ

0.60

 numerus

0.59

__':

0.59

getSystemService

0.59

تقاوى

0.57

reszcie

0.57

UrlResolution

0.56

UnusedPrivate

0.55

Activations Density 0.359%

information on reading levels of books, specifically grade levels

references to educational levels or grades

grade

No Known Activations