INDEX

Explanations

references to political entities and their actions

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

ending in "s"

np_acts-logits-general · gemini-2.0-flash

possessive followed by noun/adjective

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

AddTagHelper

-0.76

(!__

-0.73

UpInside

-0.71

ioutil

-0.69

djangoproject

-0.69

RegressionTest

-0.65

company

-0.65

 company

-0.65

 LoggerFactory

-0.64

yntaxException

-0.64

POSITIVE LOGITS

 newest

0.72

own

0.71

 inability

0.66

 woes

0.65

 stance

0.62

 ability

0.62

 relationship

0.62

 foray

0.61

 egne

0.61

 coffers

0.60

Activations Density 0.320%

references to political entities and their actions

ending in "s"

possessive followed by noun/adjective

No Comments

No Known Activations