INDEX

Explanations

structured data and regulatory terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 <<<<<<<<<<<<<<

-0.70

enumi

-0.59

 StatelessWidget

-0.56

 становника

-0.53

mpo

-0.51

').

-0.51

hadores

-0.50

 StatefulWidget

-0.49

fromnode

-0.48

.')

-0.48

POSITIVE LOGITS

 meanwhile

0.75

Conversely

0.72

 conversely

0.69

 natomiast

0.65

BeginContext

0.61

 còn

0.61

 likewise

0.61

 Conversely

0.61

 alternatively

0.59

Closer

0.58

Activations Density 0.419%

structured data and regulatory terms

No Comments

No Known Activations