INDEX

Explanations

statements that highlight surprising or unexpected outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

antMatchers

-0.65

DispatchToProps

-0.59

AnimationsModule

-0.56

 contextLoads

-0.55

kheim

-0.55

 الرياضيه

-0.54

::_('

-0.54

BeginContext

-0.54

érience

-0.54

 esternos

-0.52

POSITIVE LOGITS

Apparently

0.91

 Apparently

0.87

 Evidently

0.78

 apparently

0.76

apparently

0.74

 evidently

0.73

webElementXpaths

0.68

どうやら

0.62

Evid

0.62

тря

0.58

Activations Density 0.158%

statements that highlight surprising or unexpected outcomes

No Comments

No Known Activations