INDEX

Explanations

terms related to data dumping and process identifiers (PIDs)

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•Gemma cluster 5

No Comments

Negative Logits

TypedDataSet

-0.73

yya

-0.60

oriasis

-0.57

 pengh

-0.56

 nonatomic

-0.55

gad

-0.55

unque

-0.55

Gad

-0.53

sedi

-0.53

iastes

-0.52

POSITIVE LOGITS

 dumps

1.05

 dump

1.05

 dumping

0.93

dumps

0.93

 dumped

0.92

 Dump

0.87

Bun

0.80

Dump

0.80

DUMP

0.79

Bun

0.78

Activations Density 0.062%

terms related to data dumping and process identifiers (PIDs)

No Comments

No Known Activations