INDEX

Explanations

elements discussing impact and evaluation in studies and their implications

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

 itſelf

-0.61

 getPlayer

-0.57

 houſe

-0.55

nodoc

-0.54

 Mucha

-0.54

 Tigre

-0.54

 lèvres

-0.54

 tranſ

-0.52

 ſtate

-0.52

 Houſe

-0.51

POSITIVE LOGITS

 betweenstory

0.62

 pinulongan

0.60

not

0.59

QMetaType

0.58

fjspx

0.57

LookAnd

0.57

といっても

0.56

protoc

0.56

 gyhoeddwyd

0.54

TypedDataSet

0.54

Activations Density 0.469%

elements discussing impact and evaluation in studies and their implications

No Comments

No Known Activations