INDEX

Explanations

references to historical events and related criticisms of power structures

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

writeFieldEnd

-0.78

kaŭ

-0.65

μαν

-0.64

 doubtnut

-0.64

makeConstraints

-0.64

Efq

-0.62

 Anſ

-0.61

AddHtmlAttribute

-0.60

#+#

-0.60

WaitGroup

-0.59

POSITIVE LOGITS

us

2.72

me

2.55

him

2.42

 them

2.41

you

1.72

them

1.68

him

1.42

 THEM

1.41

eux

1.35

lui

1.23

Activations Density 1.964%

references to historical events and related criticisms of power structures

No Comments

No Known Activations