INDEX

Explanations

text related to procedures and descriptions of experiments

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

Followed by a sequential action

np_acts-logits-general · gemini-2.0-flash

what comes next

np_acts-logits-general · gemini-2.5-flash-lite

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

 дописавши

-0.65

expandindo

-0.61

معلومات

-0.60

__(/*!

-0.56

awtextra

-0.53

linearGradient

-0.51

didReceive

-0.51

værende

-0.51

üğü

-0.50

 tartalomajánló

-0.50

POSITIVE LOGITS

 then

4.21

then

3.50

Then

3.48

 Then

3.46

 THEN

3.10

THEN

2.72

 سپس

2.64

 затем

2.57

 kemudian

2.52

 puis

2.52

Activations Density 1.521%

text related to procedures and descriptions of experiments

Followed by a sequential action

what comes next

No Comments

No Known Activations