INDEX

Explanations

occurrences of contextual phrases that indicate a presence or observation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 виправивши

-1.25

 ModelExpression

-1.22

DockStyle

-1.08

 AssemblyCulture

-1.08

 ujednoznacz

-1.07

Tikang

-1.03

المناصب

-1.01

MemoryWarning

-0.99

SharedDtor

-0.97

 المعيارى

-0.96

POSITIVE LOGITS

The

1.35

There

1.13

It

1.03

The

1.02

 There

0.97

In

0.94

This

0.94

It

0.86

As

0.84

Although

0.81

Activations Density 0.068%

occurrences of contextual phrases that indicate a presence or observation

No Comments

No Known Activations