INDEX

Explanations

references to encounters with marine life, particularly sharks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

็ง

-0.57

 pomoc

-0.49

ればいい

-0.47

acchi

-0.46

Toponymie

-0.46

 sinyal

-0.45

uci

-0.45

 henvis

-0.44

榄

-0.44

 Hecht

-0.43

POSITIVE LOGITS

Personendaten

0.67

 closeness

0.67

InputBorder

0.64

 close

0.61

 AssemblyProduct

0.61

 intimacy

0.60

Closer

0.59

новништво

0.59

onViewCreated

0.59

 intimate

0.59

Activations Density 0.275%

references to encounters with marine life, particularly sharks

No Comments

No Known Activations