INDEX

Explanations

references to lakes and ponds

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

 myſelf

-0.91

 themſelves

-0.86

Efq

-0.84

 متعلقه

-0.84

 xenia

-0.83

parsedMessage

-0.81

 Varian

-0.81

 himſelf

-0.81

 itſelf

-0.80

BASEPATH

-0.79

POSITIVE LOGITS

 Lake

2.69

 lake

2.46

Lake

2.38

 lakes

2.26

 LAKE

2.17

 Lakes

2.06

lake

2.06

LAKE

1.86

lakes

1.82

Lakes

1.81

Activations Density 0.048%

references to lakes and ponds

No Comments

No Known Activations