INDEX

Explanations

words that refer to food

oai_token-act-pair · gemini-2.0-flash

technical or programming-related terminology

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

food descriptions

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

erequisite

-0.56

ivotopis

-0.56

abetes

-0.53

aquin

-0.52

 Rembrandt

-0.51

клопе

-0.49

 Avic

-0.49

AsStream

-0.49

 LIRE

-0.49

Obl

-0.48

POSITIVE LOGITS

########.

0.83

 mergeFrom

0.65

Personensuche

0.62

protoimpl

0.57

:+:

0.57

 OMITBAD

0.56

 Pfeffer

0.55

 estimés

0.55

tagHelperRunner

0.55

thouse

0.55

Activations Density 0.871%

words that refer to food

technical or programming-related terminology

food descriptions

No Comments

No Known Activations