INDEX

Explanations

database schema definitions and data types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تقاوى

-0.82

aarrggbb

-0.61

 viewType

-0.61

 propOrder

-0.60

 informée

-0.58

ValueStyle

-0.57

 समीक्षाओं

-0.56

onPressed

-0.55

 Италијани

-0.55

 EconPapers

-0.54

POSITIVE LOGITS

 maxLength

0.67

BeginContext

0.64

 length

0.64

 characters

0.62

长度

0.59

HasMaxLength

0.58

length

0.58

Length

0.54

maxlength

0.54

MAX

0.54

Activations Density 0.077%

database schema definitions and data types

No Comments

No Known Activations