INDEX

Explanations

technical terms and identifiers related to programming and coding structures

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

Strings followed by a quotation mark

np_acts-logits-general · gemini-2.0-flash

code identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 recev

-0.52

 SURVEY

-0.52

mique

-0.51

hoid

-0.51

 Técnicas

-0.48

ició

-0.47

Вопросы

-0.47

entiel

-0.47

 canlynol

-0.46

érée

-0.46

POSITIVE LOGITS

bParam

0.82

}{*}{

0.69

iLocal

0.67

AS

0.67

 виправивши

0.66

/*

0.65

 صوتيه

0.65

AN

0.64

NameInMap

0.64

WithIOException

0.63

Activations Density 0.409%

technical terms and identifiers related to programming and coding structures

Strings followed by a quotation mark

code identifiers

No Comments

No Known Activations