INDEX

Explanations

uncertainty and conditional phrases related to possibilities or potential outcomes

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

 regular

-0.47

 SEDS

-0.43

 suivante

-0.42

NamedQueries

-0.40

مصادر

-0.40

 اط

-0.39

pra

-0.39

FieldNumber

-0.39

assurer

-0.39

pro

-0.38

POSITIVE LOGITS

oredCriteria

0.82

 Italijanski

0.79

anskje

0.78

 pourraient

0.72

 '\\;'

0.71

 nakalista

0.70

írit

0.70

XmlAccessorType

0.70

 CreateTagHelper

0.70

 könnte

0.69

Activations Density 0.289%

uncertainty and conditional phrases related to possibilities or potential outcomes

No Comments

No Known Activations