INDEX

Explanations

quantitative data and percentages related to research metrics or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ernoo

-0.58

-0.54

र्क

-0.53

NotImplemented

-0.50

godic

-0.50

οιν

-0.48

paedic

-0.48

getSupport

-0.48

спеди

-0.48

 חיצוניים

-0.48

POSITIVE LOGITS

 Paglinawan

1.01

 '\\;'

0.87

发表于

0.79

tiny

0.78

Tiny

0.74

 tiny

0.74

SourceChecksum

0.73

 Infórmanos

0.73

saraba

0.72

 Tiny

0.72

Activations Density 0.669%

quantitative data and percentages related to research metrics or results

No Comments

No Known Activations