INDEX

Explanations

mentions of the name "Don."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

View

-0.67

-0.66

In

-0.64

op

-0.62

<eos>

-0.61

de

-0.61

Before

-0.60

opo

-0.59

The

-0.58

POSITIVE LOGITS

Isn

1.45

Isn

1.44

doesn

1.34

 Shouldn

1.33

 Wasn

1.31

 wouldn

1.31

 Aren

1.30

Doesn

1.30

 weren

1.30

 shouldn

1.29

Activations Density 0.156%

mentions of the name "Don."

No Comments

No Known Activations