INDEX

Explanations

statements made by sources, particularly in the context of reporting or insider information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

tvguidetime

-0.62

typename

-0.60

DotNetBar

-0.55

 везе

-0.54

AspNet

-0.54

MENAFN

-0.54

BrowserModule

-0.54

rück

-0.53

zera

-0.53

ENGL

-0.53

POSITIVE LOGITS

ArrowToggle

0.62

bootstrapcdn

0.61

 sources

0.53

 NSError

0.51

olic

0.50

 stratégique

0.47

 overheard

0.45

ródła

0.44

 estratégico

0.44

 initComponents

0.44

Activations Density 0.093%

statements made by sources, particularly in the context of reporting or insider information

No Comments

No Known Activations