INDEX

Explanations

phrases that refer to various versions or adaptations of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 يتيمه

-0.79

IsContent

-0.72

AddTagHelper

-0.59

 الحره

-0.59

:][

-0.57

AndEndTag

-0.56

FailureListener

-0.56

elemField

-0.55

 Medea

-0.54

POSITIVE LOGITS

شهاد

0.65

PyExc

0.55

Архівовано

0.55

genossen

0.53

izophren

0.53

jaciół

0.52

 یعنی

0.51

itemType

0.50

 hypocrite

0.50

omenclature

0.50

Activations Density 0.450%

phrases that refer to various versions or adaptations of something

No Comments

No Known Activations