INDEX

Explanations

references to individuals or groups

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

"person" or its variations

np_acts-logits-general · gemini-2.0-flash

person and related phrases

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

ArgsConstructor

-1.05

 WebDriverWait

-0.90

ConstraintMaker

-0.89

 EconPapers

-0.89

BagLayout

-0.88

 RouterModule

-0.81

HomeAsUpEnabled

-0.81

argout

-0.80

]")]

-0.80

RetentionPolicy

-0.78

POSITIVE LOGITS

who

0.86

 Persons

0.82

 PERSON

0.80

 Person

0.77

Persons

0.77

ification

0.77

 PERSONS

0.74

 persons

0.73

 person

0.72

persons

0.70

Activations Density 0.051%

references to individuals or groups

"person" or its variations

person and related phrases

No Comments

No Known Activations