INDEX

Explanations

references to goals or objectives

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

ники

-0.53

It

-0.52

 madrugada

-0.52

 seguito

-0.50

its

-0.49

tissimo

-0.48

 parezca

-0.48

sə

-0.47

avier

-0.47

 bedien

-0.47

POSITIVE LOGITS

 goal

3.67

 Goal

3.50

goal

3.44

Goal

3.27

 GOAL

3.20

 goals

2.99

 Goals

2.92

GOAL

2.82

goals

2.77

Goals

2.70

Activations Density 0.081%

references to goals or objectives

No Comments

No Known Activations