INDEX

Explanations

programming-related terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ühm

-0.59

ⓧ

-0.54

zola

-0.52

fördert

-0.50

mographie

-0.49

 Henrietta

-0.49

__'

-0.49

 Corintios

-0.49

 كورة

-0.48

 wzor

-0.48

POSITIVE LOGITS

клопе

0.77

posedge

0.73

 Normdatei

0.62

WebVitals

0.60

archiviato

0.59

رشف

0.58

jfree

0.56

AndEndTag

0.55

 <=",

0.52

 newBuilder

0.52

Activations Density 0.149%

programming-related terms and functions

No Comments

No Known Activations