INDEX

Explanations

situations involving shock and surprise, often related to emotional responses

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

devamını

-0.60

octanol

-0.60

 MenuView

-0.58

UrlResolution

-0.57

expandindo

-0.55

logan

-0.54

 SONS

-0.54

ocell

-0.53

hidupan

-0.52

ecore

-0.52

POSITIVE LOGITS

 stunned

1.07

 shocked

1.01

 bewildered

0.94

 dumbfounded

0.90

 confused

0.88

 perplexed

0.85

 dazed

0.84

 puzzled

0.83

 surprised

0.82

 astonished

0.82

Activations Density 0.202%

situations involving shock and surprise, often related to emotional responses

No Comments

No Known Activations