INDEX

Explanations

phrases that indicate specific events and their conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ruptedException

-0.53

 otomatig

-0.50

Embeddable

-0.49

duction

-0.46

Lähteet

-0.45

Animating

-0.45

 investasi

-0.44

migrationBuilder

-0.44

 tibur

-0.42

❦

-0.42

POSITIVE LOGITS

 hvis

0.88

 whenever

0.86

whenever

0.82

 Apabila

0.82

Whenever

0.81

Hvis

0.80

 Whenever

0.80

 wenn

0.77

wenn

0.76

หาก

0.76

Activations Density 0.375%

phrases that indicate specific events and their conditions

No Comments

No Known Activations