INDEX

Explanations

questions about the correctness or validity of statements and assumptions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

حياته

-0.63

LocationManager

-0.54

 onOptions

-0.53

nextInt

-0.49

 boku

-0.45

 بيها

-0.44

jän

-0.44

limia

-0.43

Aig

-0.43

 probate

-0.42

POSITIVE LOGITS

WebElementEntity

0.69

__*/

0.64

AxisAlignment

0.62

StructEnd

0.59

WriteBarrier

0.58

0.56

OGND

0.56

itous

0.55

 AssemblyVersion

0.54

TagHelpers

0.54

Activations Density 0.291%

questions about the correctness or validity of statements and assumptions

No Comments

No Known Activations