INDEX

Explanations

references to data types and categories in programming or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Anſ

-1.01

 Reſ

-0.90

 raiſ

-0.89

 Monfieur

-0.89

 ſee

-0.89

 nicio

-0.88

 leaſt

-0.87

ceuticals

-0.87

sizeCache

-0.86

 anſ

-0.85

POSITIVE LOGITS

 Type

1.61

 TYPE

1.56

 type

1.50

 types

1.48

type

1.40

TYPE

1.38

Type

1.35

types

1.34

 getType

1.31

 tipo

1.24

Activations Density 0.158%

references to data types and categories in programming or technical contexts

No Comments

No Known Activations