INDEX

Explanations

numeric expressions or counts related to experiences or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Билгалдахарш

-0.66

AddHtmlAttribute

-0.64

ContentLoaded

-0.63

?";

-0.63

principalColumn

-0.62

 Signalez

-0.61

PMailer

-0.61

 IndexPath

-0.60

hcm

-0.60

Filmografie

-0.60

POSITIVE LOGITS

 hennes

0.52

my

0.52

 Inscrivez

0.51

Freq

0.49

 inmediato

0.49

astéroïdes

0.49

 rağmen

0.48

 respectivement

0.48

wój

0.48

my

0.48

Activations Density 0.549%

numeric expressions or counts related to experiences or events

No Comments

No Known Activations