INDEX

Explanations

questions beginning with "how."

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

 Schulte

-0.79

 Vance

-0.77

 raft

-0.77

 Münch

-0.73

AE

-0.68

 Milne

-0.68

 Cate

-0.68

 Aires

-0.68

 pollici

-0.68

 Stein

-0.68

POSITIVE LOGITS

how

2.51

HOW

2.06

How

2.02

How

1.94

HOW

1.82

how

1.78

howto

1.35

 cómo

1.34

יצד

1.22

 Howell

1.22

Activations Density 0.067%

questions beginning with "how."

No Comments

No Known Activations