INDEX

Explanations

phrases encouraging action or suggestions

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

IUrlHelper

-0.69

contentLoaded

-0.69

InjectAttribute

-0.62

 dibat

-0.60

MigrationBuilder

-0.59

ArrowToggle

-0.58

 säll

-0.57

setopt

-0.56

CppMethod

-0.55

ⓧ

-0.54

POSITIVE LOGITS

 check

0.83

 consider

0.81

 grab

0.73

 Consider

0.72

 join

0.71

 CHECK

0.70

 seize

0.68

consider

0.65

 checking

0.64

 checkout

0.63

Activations Density 0.163%

phrases encouraging action or suggestions

No Comments

No Known Activations