INDEX

Explanations

content related to academic or scientific discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 betweenstory

-0.96

 nakalista

-0.94

 Majefty

-0.88

 leſs

-0.84

 myſelf

-0.83

 pleaſure

-0.82

 Reſ

-0.82

Eſ

-0.80

 greateſt

-0.79

 purpoſe

-0.79

POSITIVE LOGITS

etc

0.60

enderror

0.56

География

0.54

 drawable

0.50

시오

0.50

CONCURRENT

0.48

굿

0.48

 buah

0.48

ToFit

0.47

reactstrap

0.47

Activations Density 0.568%

content related to academic or scientific discussions

No Comments

No Known Activations