INDEX

Explanations

code-related terminology and syntax within programming contexts

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

drivers registration

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.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

⠀⠀⠀⠀⠀⠀⠀⠀

-0.36

<_>

-0.35

 settle

-0.35

NSIndexPath

-0.35

mockMvc

-0.33

setLength

-0.33

 memb

-0.33

 erle

-0.33

سد

-0.32

moveToNext

-0.32

POSITIVE LOGITS

 drivers

0.68

 registration

0.67

 driver

0.63

Drivers

0.62

drivers

0.60

 registering

0.60

 Drivers

0.60

 registrations

0.60

 Registration

0.59

bootstrapcdn

0.56

Activations Density 0.034%

code-related terminology and syntax within programming contexts

drivers registration

No Comments

No Known Activations