INDEX

Explanations

references to different sides of a conflict or debate

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

vaz

-0.52

결

-0.45

Dur

-0.44

hac

-0.43

aux

-0.43

Time

-0.43

Aux

-0.43

尾

-0.42

ut

-0.42

Constraints

-0.42

POSITIVE LOGITS

 side

0.92

MigrationBuilder

0.80

 MainAxisSize

0.79

apunov

0.74

DockStyle

0.73

 تانيه

0.72

 متعلقه

0.72

extAlignment

0.71

commodations

0.70

 kısm

0.69

Activations Density 0.258%

references to different sides of a conflict or debate

No Comments

No Known Activations