INDEX

Explanations

instances of users discussing shared problems or experiences

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

CloseOperation

-0.72

gdx

-0.59

secta

-0.58

 الرياضيه

-0.54

 nahilalakip

-0.52

hamdulillah

-0.52

gestone

-0.52

áctenos

-0.52

UserScript

-0.51

Portale

-0.51

POSITIVE LOGITS

RegistryLite

0.65

LET

0.52

 verified

0.51

asier

0.51

letcher

0.49

 Share

0.48

 sharing

0.48

LETS

0.48

 Shared

0.47

öhe

0.47

Activations Density 0.182%

instances of users discussing shared problems or experiences

No Comments

No Known Activations