INDEX

Explanations

references to knowledge and understanding 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 GONNA

-0.68

Tuf

-0.63

 sinner

-0.62

 smtplib

-0.61

 gonna

-0.61

foglal

-0.59

 Appellants

-0.59

 depolar

-0.58

 dictadura

-0.57

 calyx

-0.57

POSITIVE LOGITS

 knowledge

3.83

knowledge

3.41

 Knowledge

3.40

Knowledge

3.29

 KNOWLEDGE

2.97

 conocimiento

2.32

 conhecimento

2.15

 knowled

2.14

 conocimientos

2.12

知识

2.08

Activations Density 0.070%

references to knowledge and understanding in various contexts

No Comments

No Known Activations