INDEX

Explanations

instances of the word "thus," indicating conclusions or inferences in context

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

 autorytatywna

-0.84

NameInMap

-0.79

Autoritní

-0.68

:✨

-0.68

 ſtate

-0.67

Beijinhos

-0.66

 Савезне

-0.65

Condol

-0.65

 pinulongan

-0.64

MigrationBuilder

-0.61

POSITIVE LOGITS

The

0.62

Moreover

0.59

Whenever

0.58

Although

0.57

یس

0.57

↵

0.57

 when

0.57

sság

0.57

러나

0.57

由於

0.57

Activations Density 0.332%

instances of the word "thus," indicating conclusions or inferences in context

No Comments

No Known Activations