INDEX

Explanations

expressions or symbols commonly used in mathematical or scientific contexts

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

 betweenstory

-1.24

 Theſe

-1.14

Efq

-1.05

ſelf

-1.02

ſelves

-1.02

 Réponses

-1.00

 Reſ

-0.99

 Савезне

-0.99

 esternos

-0.98

 Roskov

-0.96

POSITIVE LOGITS

0.64

0.57

0.55

0.54

0.53

0.50

mer

0.49

మీ

0.49

。

0.48

II

0.48

Activations Density 0.070%

expressions or symbols commonly used in mathematical or scientific contexts

No Comments

No Known Activations