INDEX

Explanations

references to organizational structures and their changes

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

collocations and specific terms

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

-0.44

 coming

-0.35

).

-0.35

。

-0.34

$.

-0.33

AnchorStyles

-0.31

."

-0.31

 empresario

-0.31

".

-0.31

POSITIVE LOGITS

ագրություններ

0.66

 autorytatywna

0.64

 disambiguazione

0.60

bootstrapcdn

0.57

Transkript

0.55

indd

0.55

seamnă

0.55

queryInterface

0.54

 Miser

0.52

wiſe

0.52

Activations Density 0.110%

references to organizational structures and their changes

collocations and specific terms

No Comments

No Known Activations