INDEX

Explanations

references to individuals named Steve or Stephen

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

ReusableCell

-0.58

 referrerpolicy

-0.57

 UIFont

-0.55

 NSCoder

-0.54

laka

-0.53

mybatisplus

-0.52

/\.

-0.50

UnitTesting

-0.49

 derer

-0.49

toThrow

-0.48

POSITIVE LOGITS

 referenties

0.64

Халык

0.60

hoeddwyd

0.59

MigrationBuilder

0.57

 Roskov

0.55

 Jobs

0.54

$_['

0.52

 Hawking

0.51

ägen

0.50

Complexity

0.50

Activations Density 0.094%

references to individuals named Steve or Stephen

No Comments

No Known Activations