INDEX

Explanations

references to the name or character "Dam."

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

IsMutable

-0.69

setVerticalGroup

-0.54

 AssemblyTitle

-0.51

addHeader

-0.51

Personendaten

-0.50

 bParam

-0.49

Наводи

-0.49

ogonal

-0.49

 unloaded

-0.48

 intemper

-0.48

POSITIVE LOGITS

dam

0.75

Dam

0.75

DoubleQuotes

0.73

dam

0.73

URLException

0.69

parsedMessage

0.69

Dam

0.67

DeleteBehavior

0.67

+#+#

0.66

DAM

0.65

Activations Density 0.076%

references to the name or character "Dam."

No Comments

No Known Activations