INDEX

Explanations

categories and classifications related to various fields and topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

 appendix

-0.40

 Früh

-0.39

appendix

-0.38

 userSchema

-0.37

 אנו

-0.36

forRoot

-0.36

 misunderstand

-0.35

!')

-0.34

 welcome

-0.34

 faute

-0.34

POSITIVE LOGITS

 Type

1.01

 Date

0.96

Type

0.93

 Location

0.93

Date

0.86

 Status

0.86

Location

0.84

 Duration

0.82

Status

0.79

 Genre

0.77

Activations Density 0.569%

categories and classifications related to various fields and topics

No Comments

No Known Activations