INDEX

Explanations

SQL database keywords and structures

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

Proofs or image scale explanations with units

np_acts-logits-general · gemini-2.0-flash

Scale bars, Queued, Primary key, Voiced by

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

at

-0.55

<eos>

-0.54

ind

-0.50

 another

-0.48

to

-0.45

-0.44

-0.43

or

-0.43

-0.42

POSITIVE LOGITS

 سكانية

1.36

 مشين

1.13

 CreateTagHelper

1.13

setVerticalGroup

1.11

HtmlAttribute

1.07

Datuak

1.06

verifyException

1.03

styleType

1.01

awtextra

1.00

 contextLoads

0.98

Activations Density 0.819%

SQL database keywords and structures

Proofs or image scale explanations with units

Scale bars, Queued, Primary key, Voiced by

No Comments

No Known Activations