INDEX

Explanations

indicators of conflict or contention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 smtplib

-0.90

 كومونز

-0.81

큼

-0.76

 Linus

-0.75

 Barca

-0.72

 refusé

-0.72

Defect

-0.71

 Defect

-0.71

 Frick

-0.71

ệc

-0.71

POSITIVE LOGITS

................

1.47

1.01

________________

0.95

----------------

0.90

0.89

################

0.86

...............

0.85

0.84

..............

0.82

0.81

Activations Density 0.506%

indicators of conflict or contention

No Comments

No Known Activations

indicators of conflict or contention

No Comments

No Known Activations