INDEX

Explanations

references to labeled data or metadata in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 />";

-0.90

$_"

-0.86

"]));

-0.83

 htons

-0.83

")));

-0.83

ſt

-0.83

 Arkivert

-0.82

=?";

-0.79

parsedMessage

-0.78

 Pizarro

-0.78

POSITIVE LOGITS

 label

1.68

 labels

1.66

 Label

1.65

labels

1.58

 LABEL

1.56

 Labels

1.54

LABEL

1.49

label

1.49

Labels

1.49

Label

1.40

Activations Density 0.040%

references to labeled data or metadata in documents

No Comments

No Known Activations