INDEX

Explanations

arguments related to false narratives and deception in society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 henne

-0.47

you

-0.47

 calma

-0.47

знача

-0.46

 rencontr

-0.46

 rencontré

-0.45

 personally

-0.45

 classmates

-0.45

Representation

-0.45

 auprès

-0.44

POSITIVE LOGITS

脚注の使い方

0.96

tvguidetime

0.91

 autorytatywna

0.86

LookAnd

0.82

TagMode

0.77

pexpr

0.76

AddTagHelper

0.72

adaptiveStyles

0.72



0.71

AddHtmlAttribute

0.71

Activations Density 0.703%

arguments related to false narratives and deception in society

No Comments

No Known Activations