INDEX

Explanations

references to survival or surviving individuals in various 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

ituary

-0.58

المناصب

-0.57

 ability

-0.53

 resourceCulture

-0.50

IBAction

-0.49

StringTo

-0.49

RRect

-0.49

SuppressWarnings

-0.48

sw

-0.48

RNAs

-0.48

POSITIVE LOGITS

 survived

1.37

 survives

1.28

 survive

1.18

survi

1.16

 sobrevi

1.11

 surviving

1.09

 sobrevivir

1.05

 Survi

1.01

 survivors

0.99

 Survive

0.98

Activations Density 0.106%

references to survival or surviving individuals in various contexts

No Comments

No Known Activations