INDEX

Explanations

phrases and words related to developments and news events

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

bux

-0.55

cott

-0.54

Rohy

-0.52

ぶん

-0.49

jgl

-0.46

RG

-0.46

DO

-0.46

 czyli

-0.44

 fallait

-0.44

 apport

-0.44

POSITIVE LOGITS

 '\\;'

0.86

jspb

0.67

IntoConstraints

0.66

=$?

0.66

henswürdigkeiten

0.65

awtextra

0.63

guous

0.63

 endwhile

0.62

>);

0.61

__*/

0.61

Activations Density 0.286%

phrases and words related to developments and news events

No Comments

No Known Activations