INDEX

Explanations

actions and events related to opening or starting something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Personendaten

-0.84

">//

-0.71

SourceChecksum

-0.68

OGND

-0.67

 ModelExpression

-0.67

ThroughAttribute

-0.67

حياتها

-0.67

حياته

-0.65

RegistryLite

-0.64

BeginContext

-0.60

POSITIVE LOGITS

up

3.60

up

2.46

Up

2.42

Up

2.35

UP

1.78

ups

1.60

UP

1.58

 upto

1.43

 lên

1.42

アップ

1.41

Activations Density 0.442%

actions and events related to opening or starting something

No Comments

No Known Activations