INDEX

Explanations

positive and negative attributes associated with 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 @ 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

WaitGroup

-0.66

ChildScrollView

-0.65

جوايز

-0.57

ArgsConstructor

-0.56

kPa

-0.55

vités

-0.55

]]);

-0.54

 TextInputType

-0.54

MigrationBuilder

-0.53

POSITIVE LOGITS

 unlike

0.58

Unlike

0.57

 CreateTagHelper

0.57

 Unlike

0.56

 verdade

0.53

itieren

0.53

 icing

0.53

UnusedPrivate

0.52

 sostanza

0.52

 thing

0.51

Activations Density 0.204%

positive and negative attributes associated with news events

No Comments

No Known Activations