INDEX

Explanations

occurrences of the word "en"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Shakspeare

-0.77

 Shaksp

-0.77

 gills

-0.69

 Cæsar

-0.68

 Mahomet

-0.67

 Charlemagne

-0.64

 kasarigan

-0.64

DockStyle

-0.63

 empress

-0.63

 lordship

-0.63

POSITIVE LOGITS

 ocasiones

0.47

Bakgrunnsstoff

0.44

ardless

0.43

 base

0.42

fon

0.42

 spéciales

0.41

 function

0.41

ósito

0.41

 Mean

0.41

+#+#

0.40

Activations Density 0.023%

occurrences of the word "en"

No Comments

No Known Activations