INDEX

Explanations

code-related terms and phrases, particularly those associated with network protocols and data handling

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

HTTP headers and response information

np_acts-logits-general · gemini-2.0-flash

HTTP request or response components

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

ynia

-0.55

ClassNotFound

-0.51

 FileWriter

-0.48

SerializeField

-0.48

ophanes

-0.47

ág

-0.47

Dam

-0.46

pes

-0.45

Pes

-0.44

pé

-0.44

POSITIVE LOGITS

 HTTP

0.70

HTTP

0.68

 незавершена

0.61

 Headers

0.60

Headers

0.58

 CreateTagHelper

0.57

AnchorStyles

0.57

بوابة

0.57

 étoient

0.57

LabelTagHelper

0.56

Activations Density 0.608%

code-related terms and phrases, particularly those associated with network protocols and data handling

HTTP headers and response information

HTTP request or response components

No Comments

No Known Activations