INDEX

Explanations

concepts and arguments related to ideas and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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



-0.93

 Houſe

-0.83

 houſe

-0.83

 Conſ

-0.83

ſelf

-0.79

 Reſ

-0.78

 سكانية

-0.78

 Diſ

-0.76

 Inſ

-0.76

endpush

-0.74

POSITIVE LOGITS

 notion

0.94

 idea

0.94

idea

0.82

 concept

0.80

 that

0.75

of

0.65

 Idee

0.63

Idea

0.62

 concetto

0.60

 ideia

0.60

Activations Density 0.441%

concepts and arguments related to ideas and their implications

No Comments

No Known Activations