INDEX

Explanations

bold or italicized text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Klin

-0.77

 angeles

-0.70

fout

-0.70

 Angeles

-0.67

<tr>

-0.65

lin

-0.64

coln

-0.64

Zal

-0.63

xr

-0.63

COLN

-0.63

POSITIVE LOGITS

]**

1.31

.**

1.20

(**

1.17

'**

1.16

)**

1.16

**

1.14

kwargs

1.08

,**

1.07

:**

0.95

 ***!

0.92

Activations Density 0.411%

bold or italicized text

No Comments

No Known Activations