INDEX

Explanations

the presence of negative values or references to negative outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

HasOne

-0.51

igt

-0.45

 gainera

-0.45

 Progressives

-0.45

Play

-0.44

 playing

-0.43

חק

-0.43

 Aires

-0.43

igth

-0.42

 spelen

-0.42

POSITIVE LOGITS

abetes

0.78

 مرئيه

0.77

expandindo

0.68

Efq

0.65

 Monfieur

0.65

 سكانية

0.64

المناصب

0.63

 tremp

0.59

 Hopf

0.58

EndContext

0.58

Activations Density 0.096%

the presence of negative values or references to negative outcomes

No Comments

No Known Activations