INDEX

Explanations

references to academic journals and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 itſelf

-1.00

دانشنامهٔ

-0.97

 Shakspeare

-0.93

 pleaſure

-0.93

 purpoſe

-0.92

 himſelf

-0.91

 themſelves

-0.90

 myſelf

-0.90

########.

-0.89

ResumeLayout

-0.85

POSITIVE LOGITS

0.49

0.43

0.41

che

0.40

0.39

 Series

0.38

0.37

 series

0.37

Series

0.37

Activations Density 0.202%

references to academic journals and publications

No Comments

No Known Activations