INDEX

Explanations

notations and references to mathematical or scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ctest

-0.62

 Résultat

-0.55

ptest

-0.55

AddTagHelper

-0.52

้อง

-0.52

stretchr

-0.51

Результа

-0.50

Risultati

-0.49

 experiment

-0.48

gql

-0.48

POSITIVE LOGITS

 overview

0.74

OGND

0.65

growing

0.59

woordig

0.59

 Lecture

0.59

 growing

0.59

 summarizing

0.58

NUMX

0.58

 summarise

0.57

Бахар

0.57

Activations Density 0.431%

notations and references to mathematical or scientific concepts

No Comments

No Known Activations