INDEX

Explanations

terms related to medical conditions and anatomical features

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

ValueStyle

-0.69

AddTagHelper

-0.66

 doInBackground

-0.64

EndInit

-0.61

 تانيه

-0.60

UseVisualStyle

-0.60

 Walkover

-0.57

UnitTesting

-0.56

IsContent

-0.56

setLayoutManager

-0.54

POSITIVE LOGITS

 facial

1.76

 face

1.61

 Face

1.52

 Facial

1.50

 faces

1.46

Facial

1.41

Face

1.40

facial

1.37

face

1.36

 FACE

1.31

Activations Density 0.288%

terms related to medical conditions and anatomical features

No Comments

No Known Activations