INDEX

Explanations

method names related to getting and setting values

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

 فريبيس

-0.65

 للاسماء

-0.60

<",

-0.59

BeginContext

-0.58

 Ciò

-0.57

CodedInputStream

-0.57

ContentAlignment

-0.56

FunctionFlags

-0.56

Personensuche

-0.56

>",

-0.55

POSITIVE LOGITS

Portale

0.80

最快更新

0.73

0.72

adeloupe

0.72

->___

0.65

PERATURE

0.63

tyard

0.62

ANT

0.62

minal

0.60

rably

0.59

Activations Density 0.050%

method names related to getting and setting values

No Comments

No Known Activations