INDEX

Explanations

terms related to data serialization and manipulation in programming contexts

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

ending in "ed"

np_acts-logits-general · gemini-2.0-flash

completed actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.88

enumi

-0.82

GraphicsUnit

-0.75

 nonatomic

-0.68

withIdentifier

-0.68

AndEndTag

-0.68

पया

-0.67

 متعلقه

-0.66

Portale

-0.66

jooq

-0.65

POSITIVE LOGITS

GED

0.68

RIED

0.68

ged

0.67

rafted

0.62

ness

0.62

aed

0.62

ashed

0.61

Brought

0.61

 ered

0.61

HED

0.59

Activations Density 1.522%

terms related to data serialization and manipulation in programming contexts

ending in "ed"

completed actions

No Comments

No Known Activations