INDEX

Explanations

text describing a positive customer service experience

oai_token-act-pair · gemini-2.0-flash

verbs indicating promptness or action

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

positive reviews

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

LookAnd

-0.74

IGraphics

-0.73

ioutil

-0.69

ValueStyle

-0.65

 ivelany

-0.64

AddTagHelper

-0.64

 lenker

-0.61

IVEREF

-0.61

RepeatedField

-0.60

 estimés

-0.60

POSITIVE LOGITS

manni

0.49

 stayed

0.47

 addressed

0.47

☸

0.44

 installed

0.44

торая

0.44

 always

0.43

 kept

0.43

 vested

0.42

 mẽ

0.42

Activations Density 0.823%

text describing a positive customer service experience

verbs indicating promptness or action

positive reviews

No Comments

No Known Activations