INDEX

Explanations

words that indicate the scale or scope of systems or concepts

oai_token-act-pair · gemini-2.0-flash

variations of the word "level."

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

level

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RegressionTest

-0.74

 الدولى

-0.54

IPAC

-0.52

TagHelper

-0.49

HostException

-0.49

openConnection

-0.48

yntaxException

-0.47

chengladbach

-0.47

JspWriter

-0.45

 Fewer

-0.44

POSITIVE LOGITS

 level

3.30

level

2.98

 Level

2.73

 LEVEL

2.72

Level

2.72

LEVEL

2.47

 nível

2.14

 nivel

2.11

 niveau

2.11

 levels

2.09

Activations Density 2.752%

words that indicate the scale or scope of systems or concepts

variations of the word "level."

level

No Comments

No Known Activations