INDEX

Explanations

equalities or assignments in programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

évaluateur

-0.67

},[])

-0.66

Geplaatst

-0.66

"},

-0.64

oa̍t

-0.62

"})

-0.62

>')

-0.61

pulos

-0.61

')))

-0.61

ļa

-0.60

POSITIVE LOGITS

 doInBackground

0.71

posedge

0.64

 AssemblyTitle

0.61

addCriterion

0.54

Ashlee

0.54

 MainAxisSize

0.53

 dals

0.52

 cref

0.52

 combattre

0.51

 financières

0.51

Activations Density 0.220%

equalities or assignments in programming syntax

No Comments

No Known Activations