INDEX

Explanations

references to specific days and temporal phrases

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

Time words

np_max-act-logits · gemini-2.0-flash Triggered by @johnny

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Wex

-0.64

ကိုးကား

-0.59

Ārējās

-0.59

piecze

-0.59

)$/,

-0.59

 außer

-0.57

[]=$

-0.57

cendental

-0.57

ɜ

-0.57

aderie

-0.57

POSITIVE LOGITS

 tomorrow

1.59

 tonight

1.52

 yesterday

1.50

 today

1.34

yesterday

1.28

tomorrow

1.18

 demain

1.11

 Tomorrow

1.10

Tomorrow

1.10

 Yesterday

1.08

Activations Density 0.143%

references to specific days and temporal phrases

Time words

No Comments

No Known Activations