INDEX

Explanations

sentences about nature trails where the reader is addressed directly

oai_token-act-pair · gemini-2.0-flash

terms related to viewing or observing

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

watching/seeing

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

Portail

-0.60

itinéraire

-0.56

 ích

-0.54

 ouvriers

-0.52

yntaxException

-0.52

 xenia

-0.52

 חיצוניים

-0.49

RuleContext

-0.49

ніципалі

-0.48

OfWork

-0.47

POSITIVE LOGITS

 watch

0.66

setViewportView

0.63

 observe

0.59

 watched

0.59

httphttps

0.59

haria

0.58

watch

0.57

 watching

0.56

 seen

0.55

cticut

0.55

Activations Density 1.550%

sentences about nature trails where the reader is addressed directly

terms related to viewing or observing

watching/seeing

No Comments

No Known Activations