INDEX

Explanations

references to rivers

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

躇

-0.94

 Roskov

-0.92

MessageTagHelper

-0.89

 noDo

-0.83

UrlResolution

-0.82

UIControlState

-0.81

ngdoc

-0.81

 myſelf

-0.81

 himſelf

-0.77

 nakalista

-0.76

POSITIVE LOGITS

 River

2.39

 river

2.31

River

2.21

 rivers

2.18

 RIVER

2.05

 Rivers

1.90

Rivers

1.83

 Rivera

1.73

river

1.73

rivers

1.63

Activations Density 0.043%

references to rivers

No Comments

No Known Activations