INDEX

Explanations

references to specific towns or town-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Karlsruhe

-0.74

 MediatR

-0.73

BuilderFactory

-0.68

dicas

-0.66

eriksaan

-0.63

imir

-0.62

 Schulte

-0.62

ンダント

-0.62

<<<<<<<<

-0.61

 Arias

-0.61

POSITIVE LOGITS

 town

3.48

 Town

3.16

 TOWN

3.01

Town

2.94

town

2.72

 towns

2.58

TOWN

2.52

towns

2.18

 Towns

2.10

Towns

1.87

Activations Density 0.040%

references to specific towns or town-related terminology

No Comments

No Known Activations