INDEX

Explanations

negative connotations and terms related to dishonesty or deceit

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 foule

-0.63

 agrico

-0.58

 popolare

-0.57

↵

-0.57

 abbildung

-0.56

 ainfi

-0.52

。

-0.51

mení

-0.51

 אחרים

-0.50

POSITIVE LOGITS

 كومونز

0.96

)$_

0.87

]='\

0.85

 getM

0.84

ugeot

0.83

éphane

0.81

ulongan

0.81

TagMode

0.78

hésite

0.78

ſſer

0.77

Activations Density 0.803%

negative connotations and terms related to dishonesty or deceit

No Comments

No Known Activations