INDEX

Explanations

numerical values and data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Efq

-0.84

 raiſ

-0.84

InjectAttribute

-0.83

 Theſe

-0.80

 ―――――

-0.75

Hauptartikel

-0.74

 myſelf

-0.74

eſt

-0.73

 poffe

-0.72

 becauſe

-0.72

POSITIVE LOGITS

 stessi

0.50

HtmlAttribute

0.50

ptăm

0.46

TargetException

0.45

HSSF

0.43

 jinak

0.42

DebuggerNonUser

0.41

Tham

0.41

 тю

0.41

Pencil

0.40

Activations Density 0.174%

numerical values and data points

No Comments

No Known Activations