INDEX

Explanations

statements emphasizing the significance or exclusivity of certain elements or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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



-1.03

expandindo

-0.94

ImageContext

-0.80

ConstraintMaker

-0.77

 betweenstory

-0.74

 MainAxisSize

-0.73

Clik

-0.73

 gynhyrchwyd

-0.72

 Monfieur

-0.72

 Biôgrafia

-0.71

POSITIVE LOGITS

 result

0.60

 reason

0.58

aim

0.57

*}\

0.55

[]):

0.54

 final

0.54

 main

0.53

deviantart

0.53

fix

0.51

<bos>

0.50

Activations Density 0.382%

statements emphasizing the significance or exclusivity of certain elements or conditions

No Comments

No Known Activations