INDEX

Explanations

prepositions indicating location or direction

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

 ſche

-0.77

 ་་

-0.77

 themſelves

-0.77

 iſt

-0.76

 iconFacebook

-0.76

 Majefty

-0.76

 ―――――

-0.76

 poffible

-0.73

 itſelf

-0.73

 Monfieur

-0.73

POSITIVE LOGITS

в

1.37

В

1.05

В

1.03

у

0.82

в

0.76

к

0.75

з

0.74

ў

0.74

द

0.74

Activations Density 0.023%

prepositions indicating location or direction

No Comments

No Known Activations