INDEX

Explanations

references to specific dates, particularly in July

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

er

-0.97

-0.79

 Peres

-0.75

es

-0.74

edm

-0.73

esen

-0.71

 שוליים

-0.71

ه

-0.70

ENO

-0.69

Berna

-0.69

POSITIVE LOGITS

 Luglio

1.07

 JULY

1.02

 July

1.01

 luglio

0.98

 julho

0.96

JULY

0.96

 Kaly

0.94

July

0.91

Seventh

0.89

 Seventh

0.89

Activations Density 0.119%

references to specific dates, particularly in July

No Comments

No Known Activations