INDEX

Explanations

text from technical documents that contains attributes, measurements and specifications

oai_token-act-pair · gemini-2.0-flash

variations of the word "make"

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

make

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

 للمعارف

-0.52

lanır

-0.47

 EdgeInsets

-0.46

oredCriteria

-0.43

Portail

-0.43

 Paglinawan

-0.42

+:+

-0.42

 olympique

-0.41

 insuffisamment

-0.41

NotBe

-0.41

POSITIVE LOGITS

 making

2.59

 make

2.53

 makes

2.47

 Making

2.45

make

2.41

Making

2.41

 Make

2.33

Make

2.31

making

2.31

makes

2.28

Activations Density 2.404%

text from technical documents that contains attributes, measurements and specifications

variations of the word "make"

make

No Comments

No Known Activations