INDEX

Explanations

mentions of actions related to receiving or obtaining items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 resourceCulture

-0.66

RegressionTest

-0.55

 onCreateView

-0.53

erol

-0.49

HasColumnType

-0.47

 GetEnumerator

-0.46

 defaultstate

-0.45

 getItemId

-0.45

esk

-0.44

 चीज़ों

-0.43

POSITIVE LOGITS

 itſelf

0.87

 themſelves

0.83

 purpoſe

0.78

 hacerlo

0.77

 himſelf

0.77

 melakukannya

0.75

 zelve

0.73

 myſelf

0.69

 reaſon

0.69

ſt

0.64

Activations Density 0.436%

mentions of actions related to receiving or obtaining items

No Comments

No Known Activations