INDEX

Explanations

special characters and mathematical notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Loma

-0.71

 Carmichael

-0.69

prep

-0.68

 Gilman

-0.67

nicity

-0.65

 Chop

-0.64

 hende

-0.63

 Weldon

-0.63

 Sanderson

-0.63

mael

-0.63

POSITIVE LOGITS

\]

2.41

}\]

1.28

\]

1.11

</blockquote>

1.04

 ostavi

1.03

例文帳に追加

0.96

findpost

0.96

″]

0.95

.*")]

0.93

">)</

0.92

Activations Density 0.209%

special characters and mathematical notation

No Comments

No Known Activations