INDEX

Explanations

phrases related to technical descriptions and measurements in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 occaf

-0.63

 reaſon

-0.63

 Offisielt

-0.63

 pleaſure

-0.63

 houſe

-0.62

 purpoſe

-0.60

 Majefty

-0.59

 themſelves

-0.58

 fevere

-0.57

 fubject

-0.55

POSITIVE LOGITS

elemField

0.79

principalTable

0.70

 betweenstory

0.63

styleType

0.63

GEBURTSDATUM

0.62

 MenuView

0.62

 invokingState

0.59

NameInMap

0.59

 himo

0.59

 AssemblyProduct

0.58

Activations Density 1.597%

phrases related to technical descriptions and measurements in scientific contexts

No Comments

No Known Activations