INDEX

Explanations

phrases indicating significant durations or assessments related to time or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 kasarigan

-0.47

پیوند

-0.44

rü

-0.44

ryt

-0.42

inois

-0.42

arked

-0.41

 arrived

-0.41

 Unies

-0.39

ypus

-0.39

 voorkomen

-0.39

POSITIVE LOGITS

 over

1.39

 OVER

1.21

 Over

1.09

 över

1.06

over

1.02

Over

1.01

 über

1.01

RegistryLite

0.99

mergeFrom

0.95

 над

0.93

Activations Density 0.201%

phrases indicating significant durations or assessments related to time or context

No Comments

No Known Activations