INDEX

Explanations

structured data or notation in the form of lists, figures, and mathematical representations

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

figure references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ParallelGroup

-0.57

 مشين

-0.57

 Infórmanos

-0.53

 EconPapers

-0.51

 invierno

-0.49

 Allí

-0.49

 незавершена

-0.48

Hentet

-0.48

 poveznice

-0.47

 curé

-0.46

POSITIVE LOGITS

@"/

0.39

 href

0.38

apimachinery

0.37

ByUrl

0.37

ped

0.36

 iconTwitter

0.36

 http

0.35

Pied

0.35

bee

0.34

ath

0.34

Activations Density 0.111%

structured data or notation in the form of lists, figures, and mathematical representations

figure references

No Comments

No Known Activations