INDEX

Explanations

numerical values or references to time and duration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

GEBURTSDATUM

-0.61

)}-\

-0.53

itosti

-0.51

inheritdoc

-0.50

 adev

-0.48

Gweler

-0.47

rani

-0.46

WireFormat

-0.45

vacy

-0.44

 trampa

-0.44

POSITIVE LOGITS

 years

0.75

 percent

0.68

 consecutive

0.68

 different

0.65

th

0.62

الإنجليزية

0.61

(!)

0.61

 cents

0.59

OnAdd

0.59

 minutes

0.58

Activations Density 0.755%

numerical values or references to time and duration

No Comments

No Known Activations