INDEX

Explanations

significant phrases or structures that suggest causation or explanation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

band

-0.52

ask

-0.51

 bells

-0.48

 contener

-0.48

__(/*!

-0.47

-0.46

 require

-0.45

Ask

-0.45

ASK

-0.45

 receb

-0.45

POSITIVE LOGITS

 Damit

1.06

Damit

0.99

 Dadurch

0.92

 waarmee

0.87

 damit

0.87

 Somit

0.84

 thereby

0.78

 womit

0.78

AsUp

0.77

 dermed

0.77

Activations Density 0.236%

significant phrases or structures that suggest causation or explanation

No Comments

No Known Activations