INDEX

Explanations

numeric values and measurements related to scientific data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gebra

-0.53

icas

-0.43

 fresas

-0.43

 greu

-0.43

agem

-0.42

getDeclared

-0.42

untu

-0.42

ngel

-0.41

atura

-0.41

 diamantes

-0.41

POSITIVE LOGITS

+#+#

0.97

 Мексичка

0.89

ंदीखरीदारी

0.86

TagHelper

0.82

MigrationBuilder

0.81

postIndex

0.81

 '\\;'

0.81

theless

0.80

 Signalez

0.79

 Савезне

0.79

Activations Density 0.979%

numeric values and measurements related to scientific data

No Comments

No Known Activations