INDEX

Explanations

references to awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

WithIOException

-0.97

Personensuche

-0.89

الحياه

-0.86

 tartalomajánló

-0.85

 CreateTagHelper

-0.82

tagHelperRunner

-0.82

 насељу

-0.82

ThroughAttribute

-0.82

HtmlAttribute

-0.79

principalTable

-0.79

POSITIVE LOGITS

 winning

1.18

 award

1.14

 awarded

1.10

 winner

1.07

 Winner

1.02

 Awarded

1.01

 finalist

1.01

Winner

1.00

 Award

0.99

 nominated

0.94

Activations Density 0.328%

references to awards and recognitions

No Comments

No Known Activations