INDEX

Explanations

negative sentiments or expressions of disbelief

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

avía

-0.66

 vitae

-0.63

Gale

-0.60

erati

-0.60

PageContext

-0.59

Étienne

-0.58

 berg

-0.57

 plak

-0.57

inetto

-0.56

 laun

-0.55

POSITIVE LOGITS

 تانيه

1.13

 يتيمه

1.04

حياته

0.98

حياتها

0.94

expandindo

0.89

 للمعارف

0.86

 quæ

0.85

poptosis

0.84

0.83

 vnto

0.81

Activations Density 0.311%

negative sentiments or expressions of disbelief

No Comments

No Known Activations