INDEX

Explanations

mentions of specific geographical locations, particularly lakes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 Moos

-0.73

getStringExtra

-0.73

Sik

-0.72

siąż

-0.71

DNEY

-0.69

 considérons

-0.68

istically

-0.67

قلال

-0.67

bobox

-0.67

geant

-0.66

POSITIVE LOGITS

lakes

0.85

 lakes

0.84

NameInMap

0.79

 Lakes

0.76

Lakes

0.75

{{$

0.74

 Lester

0.71

 Lake

0.71

'.$

0.70

Lester

0.68

Activations Density 0.649%

mentions of specific geographical locations, particularly lakes

No Comments

No Known Activations