INDEX

Explanations

sentences involving accusations and denials related to wrongdoing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

top

-0.44

non

-0.43

 гр

-0.42

SuppressMessage

-0.41

 ofrec

-0.40

zd

-0.40

tende

-0.40

pa

-0.40

Pa

-0.40

стей

-0.39

POSITIVE LOGITS

 EconPapers

0.93

LookAnd

0.87

GEBURTSDATUM

0.85

RenderAtEndOf

0.83

 فريبيس

0.80

 Majefty

0.75

MLLoader

0.75

RectangleBorder

0.75

 Dicapai

0.72

 ſtate

0.72

Activations Density 0.811%

sentences involving accusations and denials related to wrongdoing

No Comments

No Known Activations