INDEX

Explanations

negations and verbs related to state or condition, particularly in the context of social implications and policy commentary

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

RegressionTest

-0.61

 RemoteException

-0.60

évaluateur

-0.59

 bVar

-0.58

ngdoc

-0.58

 bulunur

-0.57

 kullanılır

-0.56

ouille

-0.56

 estekak

-0.53

 betweenstory

-0.52

POSITIVE LOGITS

 causing

1.15

 becoming

1.13

 helping

1.12

 proving

1.08

 happening

0.94

 being

0.94

 affecting

0.93

 progressing

0.92

 impacting

0.91

 getting

0.91

Activations Density 0.335%

negations and verbs related to state or condition, particularly in the context of social implications and policy commentary

No Comments

No Known Activations