INDEX

Explanations

references to control structures or commands in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 éché

-0.79

 lèvres

-0.71

✨:

-0.71

DATASET

-0.70

 ROUTES

-0.70

 Ayers

-0.70

__':

-0.69

__':

-0.69

 Daley

-0.69

asiswa

-0.69

POSITIVE LOGITS

 control

2.28

 Control

2.13

control

2.09

 CONTROL

2.06

Control

2.05

 controls

1.96

CONTROL

1.87

 Controls

1.79

 controle

1.61

Controls

1.57

Activations Density 0.076%

references to control structures or commands in programming contexts

No Comments

No Known Activations