INDEX

Explanations

functionality related to database operations and properties

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

Followed by a list of values/arguments

np_acts-logits-general · gemini-2.0-flash

given parameters

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

<eos>

-0.65

juna

-0.49

openSession

-0.45

↵↵

-0.44

 Land

-0.44

Read

-0.44

ж

-0.43

初

-0.43

 Meksiku

-0.43

ிர

-0.43

POSITIVE LOGITS

 given

1.29

 specified

1.26

given

1.17

specified

1.08

指定的

1.03

 Specified

1.00

 GIVEN

0.94

Specified

0.93

Given

0.91

 supplied

0.88

Activations Density 0.281%

functionality related to database operations and properties

Followed by a list of values/arguments

given parameters

No Comments

No Known Activations