INDEX

Explanations

terms associated with art and cultural experiences

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

NewUrlParser

-0.83

tableFuture

-0.81

IntoConstraints

-0.77

 يتيمه

-0.75

AxisAlignment

-0.73

SequentialGroup

-0.73

MemoryWarning

-0.73

 AssemblyCulture

-0.73

IndentedString

-0.72

migrationBuilder

-0.71

POSITIVE LOGITS

 avid

1.07

 fans

1.06

 lovers

0.94

die

0.94

 ardent

0.91

 conno

0.90

 keen

0.86

 aficionados

0.85

 λά

0.84

 afic

0.83

Activations Density 0.235%

terms associated with art and cultural experiences

No Comments

No Known Activations