INDEX

Explanations

numerical values, particularly those indicating time or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cada

-0.47

diğinde

-0.41

pompa

-0.41

Ặ

-0.41

prechpartner

-0.41

 estimés

-0.40

focusable

-0.40

 surfact

-0.39

::_('

-0.39

realpath

-0.39

POSITIVE LOGITS

 half

1.60

half

1.46

 Half

1.34

Half

1.32

 HALF

1.23

HALF

1.11

半

1.11

 halves

1.07

 halve

1.01

halb

0.97

Activations Density 0.369%

numerical values, particularly those indicating time or quantities

No Comments

No Known Activations