INDEX

Explanations

references to the word "dam" and its variations in context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IsMutable

-0.65

Hochspringen

-0.64

 bParam

-0.58

Personendaten

-0.56

ChildScrollView

-0.56

mstyle

-0.55

Portale

-0.54

phosa

-0.54

 openers

-0.52

SharedDtor

-0.52

POSITIVE LOGITS

Dam

0.77

dam

0.73

dam

0.70

Dam

0.68

DAM

0.66

DeleteBehavior

0.65

parsedMessage

0.63

URLException

0.61

SEL

0.58

DoubleQuotes

0.58

Activations Density 0.061%

references to the word "dam" and its variations in context

No Comments

No Known Activations