INDEX

Explanations

words related to triggering events or actions

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

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

 viewDidLoad

-0.69

例文帳に追加

-0.66

KommentareTeilen

-0.61

 Familienname

-0.60

GIVEREF

-0.53

OCCURRED

-0.53

 урна

-0.53

通販

-0.53

\{\\

-0.52

Bioaccumulative

-0.51

POSITIVE LOGITS

')[

0.93

")[

0.85

 triggers

0.69

principalTable

0.67

 }^{\

0.66

)[

0.66

 trigger

0.65

 TRIG

0.64

 triggering

0.61

 extensions

0.61

Activations Density 0.169%

words related to triggering events or actions

No Comments

No Known Activations