INDEX

Explanations

phrases related to conditional or specific situations in studies or policies

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

DockStyle

-0.91

IsContent

-0.79

PerformLayout

-0.79

RenderAtEndOf

-0.71

abetes

-0.71

 صوتيه

-0.70

MigrationBuilder

-0.66

IContainer

-0.65

 Figura

-0.64

 يتيمه

-0.64

POSITIVE LOGITS

 keinerlei

0.66

 никаких

0.66

 otherwise

0.65

 Otherwise

0.60

 nenhum

0.60

otherwise

0.60

 OTHERWISE

0.60

 nothing

0.60

 никакого

0.60

Otherwise

0.59

Activations Density 0.375%

phrases related to conditional or specific situations in studies or policies

No Comments

No Known Activations