INDEX

Explanations

specific locations or sites mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

رشف

-0.55

StructEnd

-0.54

منى

-0.51

TagHelper

-0.50

OCK

-0.49

laught

-0.48

sozial

-0.48

ar

-0.48

 EconPapers

-0.45

considerable

-0.44

POSITIVE LOGITS

 تضيفلها

0.77

fhir

0.66

rxjs

0.58

orianCalendar

0.55

parsedMessage

0.55

 onPostExecute

0.55

dtd

0.54

typeorm

0.53

 Rosenberg

0.53

PyExc

0.53

Activations Density 0.340%

specific locations or sites mentioned in the text

No Comments

No Known Activations