INDEX

Explanations

references to judicial processes and legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

…

-0.66

ing

-0.59

ob

-0.56

er

-0.55

ve

-0.53

ers

-0.52

–

-0.51

ac

-0.51

ts

-0.50

POSITIVE LOGITS

IsContent

1.04

 pleaſure

1.03

 photolibrary

1.01

 feroit

1.01

^(@)

0.99

 greateſt

0.98

 myſelf

0.96

 poffible

0.95

RenderAtEndOf

0.95

 Houſe

0.95

Activations Density 0.225%

references to judicial processes and legal terminology

No Comments

No Known Activations