INDEX

Explanations

evidence of interactions and exchanges between characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 autorytatywna

-0.94

 Normdatei

-0.89

NUMX

-0.88

 NSCoder

-0.79

]")]

-0.76

FontOfSize

-0.74

#+#

-0.73

">:

-0.72

`,

-0.70

 onPostExecute

-0.70

POSITIVE LOGITS

↵↵

0.53

...

0.50

<eos>

0.44

Chapter

0.43

某

0.43

ו

0.41

↵

0.40

 şey

0.40

↵↵↵

0.39

Activations Density 0.063%

evidence of interactions and exchanges between characters

No Comments

No Known Activations