INDEX

Explanations

structured data related to telecommunication statistics and subscription details

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Recuperado

-0.61

 emper

-0.57

 Hesper

-0.55

ropriate

-0.54

NUMX

-0.54

URDAY

-0.54

intrag

-0.53

insics

-0.53

rozco

-0.53

ufe

-0.52

POSITIVE LOGITS

 vicini

0.71

 morire

0.67

 rosse

0.67

 nemico

0.62

 tewas

0.61

 figliu

0.60

 giebt

0.60

vgili

0.60

 tué

0.58

brtc

0.58

Activations Density 0.202%

structured data related to telecommunication statistics and subscription details

No Comments

No Known Activations