INDEX

Explanations

sections of text without any activating words or phrases

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

abestanden

-0.66

 فريبيس

-0.64

sillos

-0.52

zeera

-0.52

ksikon

-0.52

Pinch

-0.52

جوايز

-0.51

makeText

-0.51

PyTuple

-0.50

FieldNumber

-0.50

POSITIVE LOGITS

 MyBatis

1.19

ByPrimaryKey

0.61

 Anlage

0.55

íslu

0.53

mybatis

0.52

 mapper

0.50

 interviewer

0.49

mbggenerated

0.47

GraphicsUnit

0.46

écu

0.46

Activations Density 0.012%

sections of text without any activating words or phrases

No Comments

No Known Activations