INDEX

Explanations

references to specific programming constructs or data structures

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 deutscher

-0.35

__("

-0.31

__('

-0.31

 tourmaline

-0.30

|*

-0.30

 "','

-0.30

 scare

-0.30

 diesel

-0.29

cout

-0.29

"]').

-0.28

POSITIVE LOGITS

 IndexPath

5.03

NSIndexPath

1.54

IndexPath

1.34

indexPath

0.95

AtIndexPath

0.88

 indexPath

0.88

httphttps

0.82

ViewFeatures

0.78

 EdgeInsets

0.77

migrationBuilder

0.76

Activations Density 0.000%

references to specific programming constructs or data structures

No Comments

No Known Activations