INDEX

Explanations

mathematical expressions and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ValueStyle

-0.62

ModelAdmin

-0.59

Tikang

-0.56

 gravity

-0.49

PagerAdapter

-0.48

 confirming

-0.48

minify

-0.47

 Reyn

-0.47

 confirms

-0.46

ąd

-0.46

POSITIVE LOGITS

let

1.21

Let

1.12

 Suppose

1.07

 suppose

1.04

Let

1.04

 consider

1.01

 Consider

1.00

Пусть

0.99

Suppose

0.99

Consider

0.92

Activations Density 1.371%

mathematical expressions and notation

No Comments

No Known Activations