INDEX

Explanations

terms related to emotional states and interpersonal relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DockStyle

-0.81

])));

-0.78

ChildScrollView

-0.68

WebElementEntity

-0.67

%");

-0.64

ategorias

-0.64

ulemon

-0.61

hirkan

-0.61

 mahdol

-0.60

lexikon

-0.60

POSITIVE LOGITS

 actually

1.58

 perhaps

1.49

actually

1.34

 maybe

1.27

 indeed

1.22

Actually

1.20

 Actually

1.19

 apparently

1.13

perhaps

1.11

 eigenlijk

1.10

Activations Density 0.365%

terms related to emotional states and interpersonal relationships

No Comments

No Known Activations