INDEX

Explanations

phrases related to asking or seeking information

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

UseVisualStyle

-0.78

NUMX

-0.69

 insuffisamment

-0.65

:✨

-0.64

BeginContext

-0.63

WriteLiteral

-0.62

 AssemblyCompany

-0.61

 otomatig

-0.61

✨:

-0.60

OGN

-0.59

POSITIVE LOGITS

for

0.95

 desperately

0.54

 specifically

0.51

for

0.51

antikan

0.48

to

0.47

 longing

0.47

 Verstär

0.47

ForValue

0.46

InjectAttribute

0.46

Activations Density 0.089%

phrases related to asking or seeking information

No Comments

No Known Activations