INDEX

Explanations

code syntax and constructs related to handling errors and memory management

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

Rujuakan

-0.64

TestTools

-0.62

AutoScaleMode

-0.61

 Савезне

-0.55

nodoc

-0.53

 Connectez

-0.52

tvguidetime

-0.52

 thereunder

-0.52

 AppCompatTheme

-0.51

 Athene

-0.51

POSITIVE LOGITS

WriteBarrier

0.62

 Signalez

0.61

?>>

0.54

ⓧ

0.54

'));

0.53

 StatelessWidget

0.52

fæ

0.51

PasswordField

0.50

'),

0.50

aternion

0.50

Activations Density 0.279%

code syntax and constructs related to handling errors and memory management

No Comments

No Known Activations