INDEX

Explanations

descriptions of facial features and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

stang

-0.50

AddTagHelper

-0.50

 doInBackground

-0.49

hoga

-0.47

XtraGrid

-0.47

 Heel

-0.46

setLayoutManager

-0.46

atorship

-0.46

ignite

-0.45

UseVisualStyle

-0.45

POSITIVE LOGITS

 face

2.35

 faces

2.21

 Face

2.09

face

2.04

 facial

2.02

Face

2.00

 Faces

1.87

 FACE

1.87

faces

1.81

 Facial

1.76

Activations Density 0.196%

descriptions of facial features and expressions

No Comments

No Known Activations