INDEX

Explanations

references to intellectual property and patent-related terminology

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

-0.52

-0.49

 Pure

-0.47

sist

-0.46

...

-0.46

-0.45

.-

-0.45

...

-0.45

{-

-0.45

POSITIVE LOGITS

 purpoſe

0.93

 Jefus

0.90

 ſche

0.89

 ſeveral

0.88

 Theſe

0.88

 pleaſure

0.88

 itſelf

0.88

 becauſe

0.86

 ſind

0.86

 ſtate

0.85

Activations Density 0.447%

references to intellectual property and patent-related terminology

No Comments

No Known Activations