INDEX

Explanations

numerical values and comparative measurements

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

⏟

-0.63

emias

-0.57

SequentialGroup

-0.55

Own

-0.54

 regularity

-0.53

googleapis

-0.52

reth

-0.52

Dobrý

-0.51

 herunterladen

-0.51

ainya

-0.51

POSITIVE LOGITS

PreferredItem

0.82

 MenuView

0.73

 typelib

0.68

InteropServices

0.66

Personendaten

0.65

WaitGroup

0.65

 ModelExpression

0.65

 bezeichneter

0.64

MigrationBuilder

0.61

writeFieldEnd

0.60

Activations Density 0.573%

numerical values and comparative measurements

No Comments

No Known Activations