INDEX

Explanations

references to bridges in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Svensk

-0.79

 pitié

-0.78

 Romains

-0.73

 aureus

-0.73

 sauvages

-0.72

Ino

-0.71

 sauvage

-0.69

 imageNamed

-0.68

 femmin

-0.67

 Moly

-0.67

POSITIVE LOGITS

 bridges

1.71

Bridges

1.66

 Bridges

1.64

 bridge

1.56

 Bridge

1.52

Bridge

1.44

 BRIDGE

1.40

bridges

1.40

 BRID

1.39

bridge

1.36

Activations Density 0.079%

references to bridges in various contexts

No Comments

No Known Activations