INDEX

Explanations

instances of the word "lit" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

MigrationBuilder

-0.70

 externi

-0.67

 Grecian

-0.65

 belge

-0.64

 Hungarian

-0.62

 Raceway

-0.58

TagMode

-0.56

Hungarian

-0.56

 Roskov

-0.55

 tuong

-0.55

POSITIVE LOGITS

lit

1.33

Lit

1.02

lit

0.99

Lit

0.96

LIT

0.78

Son

0.77

LIT

0.74

literal

0.72

 Word

0.65

Son

0.62

Activations Density 0.048%

instances of the word "lit" in various contexts

No Comments

No Known Activations