INDEX

Explanations

references to limbs and their positioning

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Rossetti

-0.84

>");

-0.81

<<<<<<<<

-0.77

(":");

-0.77

atisfaction

-0.76

 Sama

-0.76

-0.73

Soorten

-0.73

*~

-0.71

(",");

-0.71

POSITIVE LOGITS

leg

2.34

 legs

2.27

 Legs

2.03

Leg

1.95

Leg

1.93

Legs

1.88

leg

1.82

legs

1.80

LEG

1.71

LEG

1.58

Activations Density 0.064%

references to limbs and their positioning

No Comments

No Known Activations