INDEX

Explanations

words and phrases related to data analysis and collective contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Not in Any Lists

No Comments

Negative Logits

CO

-0.48

Bar

-0.48

Men

-0.47

hik

-0.47

ogado

-0.46

 према

-0.46

 document

-0.46

bal

-0.45

CH

-0.45

Du

-0.45

POSITIVE LOGITS

 myſelf

0.88

 Theſe

0.86

 Monfieur

0.82

 itſelf

0.82

 houſe

0.82

 Houſe

0.79

 pleaſure

0.76

 ſeveral

0.75

 raiſ

0.75

ſelf

0.74

Activations Density 0.630%

words and phrases related to data analysis and collective contributions

No Comments

No Known Activations