INDEX

Explanations

references to products and specific items in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

собенности

-0.58

TestingModule

-0.56

戬

-0.55

 Normdatei

-0.53

ormais

-0.52

alnız

-0.52

 setuptools

-0.52

 ønsker

-0.51

 számára

-0.50

 كومونز

-0.50

POSITIVE LOGITS

 sound

1.25

 look

1.15

 work

1.02

 suck

1.00

 taste

0.89

 smell

0.85

 LOOK

0.82

sound

0.82

look

0.80

 Look

0.75

Activations Density 0.487%

references to products and specific items in discussions

No Comments

No Known Activations