INDEX

Explanations

sequences of repeated or commented-out asterisks

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

DataAnnotations

-0.71

LookAnd

-0.71

 אומר

-0.68

تماد

-0.66

rój

-0.66

WithIOException

-0.63

-0.62

úly

-0.62

hljs

-0.62

 obce

-0.61

POSITIVE LOGITS

****************

2.97

################

1.53

----------------

1.42

***************

1.35

************

1.33

**************

1.32

////////////////

1.32

================

1.30

*************

1.26

***********

1.22

Activations Density 0.235%

sequences of repeated or commented-out asterisks

No Comments

No Known Activations