INDEX

Explanations

terms associated with decision-making processes

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

protoc

-0.75

NSNotification

-0.62

ForResult

-0.59

shen

-0.55

AxisAlignment

-0.55

getColumnIndex

-0.54

sud

-0.54

Jü

-0.54

lü

-0.53

CardHeader

-0.53

POSITIVE LOGITS

1.25

1.16

Искәрмәләр

1.03

 صوتيه

0.96

0.91

0.86

 initComponents

0.84

AutoScaleMode

0.84

 wireType

0.82

PreferredItem

0.80

Activations Density 0.023%

terms associated with decision-making processes

No Comments

No Known Activations