INDEX

Explanations

markers indicating the beginning of new sections or important criteria within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Paglinawan

-1.08

WireFormatLite

-0.95

__':

-0.82

OGND

-0.76

ViewImports

-0.76

 kaarangay

-0.74

 Audiodateien

-0.73

хьтан

-0.72

 Roskov

-0.71

 myſelf

-0.71

POSITIVE LOGITS

 also

0.82

 again

0.67

0.65

 أيضاً

0.63

was

0.63

in

0.60

0.59

<eos>

0.58

 likewise

0.57

↵

0.56

Activations Density 1.555%

markers indicating the beginning of new sections or important criteria within a context

No Comments

No Known Activations