INDEX

Explanations

phrases indicating possession or ownership

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

OGND

-0.92

enumii

-0.77

antMatchers

-0.76

ngrx

-0.74



-0.73

 Roskov

-0.72

 ExecuteAsync

-0.71

MENAFN

-0.71

sidemargin

-0.70

 noqa

-0.69

POSITIVE LOGITS

 heard

0.82

 read

0.77

 noticed

0.64

 doubts

0.63

 tried

0.60

 talked

0.54

Read

0.53

 watched

0.52

heard

0.52

 seen

0.51

Activations Density 0.159%

phrases indicating possession or ownership

No Comments

No Known Activations