INDEX

Explanations

references to code examples or programming concepts

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

 they

-0.82

us

-0.71

 itself

-0.63

 themselves

-0.59

getLogger

-0.58

 Itself

-0.57

They

-0.57

my

-0.55

they

-0.54

 meille

-0.54

POSITIVE LOGITS

 ourselves

0.70

::_('

0.57

providedIn

0.56

enumi

0.56

دانشنامهٔ

0.55

 Mongols

0.54

ignons

0.54

kloped

0.54

 validamos

0.54

Stam

0.53

Activations Density 0.051%

references to code examples or programming concepts

No Comments

No Known Activations