INDEX

Explanations

programming constructs and identifiers related to configuration and HTTP handling

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

Code, class, and library names

np_acts-logits-general · gemini-2.0-flash

struct or class definition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

?')

-0.67

enderror

-0.64

PreferredItem

-0.61

potranspiration

-0.60

romyalgia

-0.60

ValueStyle

-0.57

 bezeichneter

-0.57

NameInMap

-0.57

 initComponents

-0.56

RTEX

-0.56

POSITIVE LOGITS

new

0.60

InitStruct

0.53

 addSubview

0.52

===

0.49

new

0.46

newly

0.45

 trus

0.44

 IndexPath

0.43

 nowo

0.43

ständen

0.42

Activations Density 0.111%

programming constructs and identifiers related to configuration and HTTP handling

Code, class, and library names

struct or class definition

No Comments

No Known Activations