INDEX

Explanations

statements or phrases that assert or highlight facts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ρους

-0.81

yntaxException

-0.81

 समीक्षक

-0.79

Autoritní

-0.77

ագրություններ

-0.75

MockBean

-0.73

 AssemblyCompany

-0.72



-0.71

RetentionPolicy

-0.70

MENAFN

-0.69

POSITIVE LOGITS

 fact

1.15

 FACT

0.95

fact

0.95

 Fact

0.91

FACT

0.88

 facts

0.83

Fact

0.82

 Facts

0.81

 Tatsache

0.71

facts

0.68

Activations Density 0.137%

statements or phrases that assert or highlight facts

No Comments

No Known Activations