INDEX

Explanations

elements related to labeling and categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 />";

-0.92

")));

-0.87

"]));

-0.86

$_"

-0.84

 htons

-0.80

 ProductService

-0.79

ſt

-0.79

=?";

-0.78

 Arkivert

-0.78

."));

-0.77

POSITIVE LOGITS

 label

1.75

 labels

1.75

 Label

1.68

labels

1.64

 Labels

1.60

 LABEL

1.58

Labels

1.54

label

1.53

LABEL

1.51

Label

1.46

Activations Density 0.050%

elements related to labeling and categorization

No Comments

No Known Activations