INDEX

Explanations

references to personal experiences and opinions

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

bootstrapcdn

-0.69

TagMode

-0.62

bati

-0.59

luor

-0.57

 utafitiHapana

-0.57

SourceChecksum

-0.56

 CONC

-0.55

UnsafeEnabled

-0.55

gonic

-0.54

POSITIVE LOGITS

 obicei

0.59

 &___

0.51

Erfolge

0.49

のように

0.48

 GenerationType

0.47

Revenir

0.47

setVerticalGroup

0.47

 professionali

0.46

より

0.46

様に

0.45

Activations Density 0.710%

references to personal experiences and opinions

No Comments

No Known Activations