INDEX

Explanations

words and phrases related to medical and mathematical concepts of positivity and continuity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

AutoScale

-0.77

+#+#

-0.69

RegistryLite

-0.68

tagext

-0.62

chengladbach

-0.61

salms

-0.60

RenderAtEndOf

-0.59

Geplaatst

-0.58

protoimpl

-0.56

gonic

-0.56

POSITIVE LOGITS

 assolu

0.76

 levels

0.71

 issues

0.65

iveau

0.64

issues

0.61

 alcanzado

0.59

 quotient

0.58

enhancing

0.58

 relativa

0.57

 niveles

0.57

Activations Density 0.604%

words and phrases related to medical and mathematical concepts of positivity and continuity

No Comments

No Known Activations