INDEX

Explanations

phrases indicating the use of deceptive or false information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

ConstraintMaker

-0.67

IntoConstraints

-0.66

migrationBuilder

-0.60

endphp

-0.57

 BorderSide

-0.55

]")]

-0.54

RenderAtEndOf

-0.54

EFE

-0.54

^(@)

-0.53

 abandonné

-0.53

POSITIVE LOGITS

øk

0.54

Edited

0.50

 Normdatei

0.50

FieldNumber

0.49

 Италијани

0.49

OrBuilder

0.48

 National

0.48

 <=",

0.48



0.47

وشن

0.47

Activations Density 0.028%

phrases indicating the use of deceptive or false information

No Comments

No Known Activations