INDEX

Explanations

phrases related to obligations and denials of responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ScopeManager

-0.54

tagHelper

-0.45

 otomatig

-0.41

蜒

-0.41

 gabbana

-0.41

asanjo

-0.41

chyma

-0.40

ьажоргаш

-0.40

EndContext

-0.40

zungs

-0.40

POSITIVE LOGITS

 anything

0.47

willReturn

0.42

IntoConstraints

0.41

一切

0.40

AutoresizingMask

0.39

 Roman

0.35

 roman

0.35

 germ

0.35

anything

0.34

 bearing

0.34

Activations Density 0.460%

phrases related to obligations and denials of responsibility

No Comments

No Known Activations