INDEX

Explanations

terms related to popularity and fame

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

BeginInit

-0.74

-0.68

anstalt

-0.66

ள்

-0.61

τ

-0.60

gms

-0.59

кви

-0.58

 niega

-0.56

Nis

-0.56

addTask

-0.55

POSITIVE LOGITS

Efq

1.52

 Theſe

1.46

 myſelf

1.42

 themſelves

1.39

 pleaſure

1.38

 whoſe

1.36

 Jefus

1.34

 Monfieur

1.34

 iſt

1.29

 faſt

1.28

Activations Density 0.054%

terms related to popularity and fame

No Comments

No Known Activations